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

    Neuronpedia

    INDEX
    Explanations

    negative command-line options in scripts or code

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

    scripting and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     userSchema
    -0.38
    aktur
    -0.38
    mployment
    -0.36
     FormGroup
    -0.35
     olahraga
    -0.35
     dessus
    -0.35
    Reprodução
    -0.35
    たら
    -0.33
     VIOL
    -0.33
    Retrieved
    -0.33
    POSITIVE LOGITS
    RTHOOK
    0.56
    CppMethod
    0.56
    matchCondition
    0.53
    0.52
     الرخصة
    0.52
    脚注の使い方
    0.51
    BeginInit
    0.51
    addGap
    0.49
     تضيفلها
    0.47
     Onion
    0.47
    Act Density 0.003%

    No Known Activations