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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific organizations, political groups, and substances used in various contexts

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

    non-|pro-|anti- words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.44
    Predecesor
    -0.39
    eradish
    -0.37
     verschil
    -0.36
     weg
    -0.36
     Мексичка
    -0.35
    MemoryWarning
    -0.35
     chofe
    -0.35
     StatelessWidget
    -0.34
    MessageOf
    -0.34
    POSITIVE LOGITS
    ⓧ
    0.47
     privately
    0.46
    tahui
    0.45
    RAFT
    0.45
     specialist
    0.44
    aryen
    0.44
     neutro
    0.44
     Camargo
    0.44
    alya
    0.42
    rager
    0.42
    Act Density 0.118%

    No Known Activations