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

    Neuronpedia

    INDEX
    Explanations

    future actions and plans

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

    followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    will be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bust
    -0.42
    mind
    -0.42
    cla
    -0.42
    SourceChecksum
    -0.42
    thinking
    -0.42
    Port
    -0.41
    InSection
    -0.40
    port
    -0.40
     cla
    -0.40
     thoughts
    -0.40
    POSITIVE LOGITS
     للاسماء
    0.59
     ligiloj
    0.57
    tagHelperRunner
    0.56
    DockStyle
    0.54
    GenerationType
    0.52
    الدراسه
    0.49
     typelib
    0.47
     prossima
    0.43
    RetentionPolicy
    0.42
    ceğine
    0.42
    Act Density 0.218%

    No Known Activations