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

    Neuronpedia

    INDEX
    Explanations

    information about settings and contextual details in various situations

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

    places and compartments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.50
    rungsseite
    -0.41
     незавершена
    -0.40
     whom
    -0.38
    acier
    -0.37
     suisse
    -0.37
     lápis
    -0.36
    WriteAttribute
    -0.36
    InputLabel
    -0.36
     AssemblyTitle
    -0.35
    POSITIVE LOGITS
    tonode
    0.60
    places
    0.59
     places
    0.58
    Anywhere
    0.56
     workplaces
    0.56
     곳
    0.56
     backyard
    0.55
     courthouse
    0.55
    berspace
    0.55
     Anywhere
    0.54
    Act Density 0.060%

    No Known Activations