Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to models and their associated metrics or performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-like outputs, models, or responses

    np_acts-logits-general · gemini-2.0-flash

    Thai film production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.48
    AutoField
    -0.47
     pyplot
    -0.44
     OFDb
    -0.41
     }{@
    -0.41
     written
    -0.41
    MLLoader
    -0.40
     AppCompatTheme
    -0.40
    DockStyle
    -0.39
     мѣ
    -0.37
    POSITIVE LOGITS
     ſte
    0.48
     humains
    0.47
     policiers
    0.46
     Anſ
    0.46
     aikaa
    0.45
     avoient
    0.45
     myſelf
    0.44
     digitais
    0.43
    enderror
    0.43
     coyote
    0.43
    Act Density 0.032%

    No Known Activations