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

    Neuronpedia

    INDEX
    Explanations

    actions and physical reactions, particularly those reflecting emotions or body language

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

    Non-verbal expressions and reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.47
     للمعارف
    -0.46
     INTERESAR
    -0.46
     Signalez
    -0.45
    peq
    -0.44
    AndEndTag
    -0.42
     Roskov
    -0.42
    клопе
    -0.41
     برانيه
    -0.40
    togen
    -0.40
    POSITIVE LOGITS
    MessageTagHelper
    0.47
     sighed
    0.46
     poveznice
    0.45
     shrugged
    0.44
     nodded
    0.44
    ękuję
    0.43
    Microkernel
    0.41
    MethodImpl
    0.40
    Hmm
    0.40
    unknownFields
    0.39
    Act Density 0.048%

    No Known Activations