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

    Neuronpedia

    INDEX
    Explanations

    identifiers related to system processes and commands

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

    log entry identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     humour
    -0.40
     avven
    -0.39
     mood
    -0.39
    ear
    -0.38
     metu
    -0.38
    COOK
    -0.35
    itattu
    -0.35
    SOFT
    -0.34
    badah
    -0.34
    ฬ
    -0.34
    POSITIVE LOGITS
    Tikang
    0.69
    Personendaten
    0.61
    fjspx
    0.60
     PeEnEo
    0.56
    rungsseite
    0.56
    GEBURTSDATUM
    0.54
    SequentialGroup
    0.54
    verifyException
    0.53
    SharedCtor
    0.52
    ſelves
    0.51
    Act Density 0.003%

    No Known Activations