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

    Neuronpedia

    INDEX
    Explanations

    expressions of knowledge and acknowledgment in various contexts

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

    little is known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.45
    存于互联网档案馆
    -0.44
    ///</
    -0.43
    DataAnnotations
    -0.43
     الرياضيه
    -0.42
     Normdatei
    -0.42
    toContain
    -0.42
     vit
    -0.42
     Keuangan
    -0.42
    tahankan
    -0.40
    POSITIVE LOGITS
     Wikiseite
    0.42
    0.39
    Referințe
    0.38
    せっかく
    0.36
     Dar
    0.36
    anniversaire
    0.35
    Cuánto
    0.35
    writeField
    0.35
    紆
    0.35
    mologie
    0.34
    Act Density 0.005%

    No Known Activations