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

    Neuronpedia

    INDEX
    Explanations

    names of countries and their relationships to citizenship and borders

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

    countries and nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.49
     attirer
    -0.46
    SequentialGroup
    -0.46
    basicConfig
    -0.44
     conmigo
    -0.43
     mijne
    -0.42
     turística
    -0.42
     cascada
    -0.41
     Gedichte
    -0.40
     botella
    -0.40
    POSITIVE LOGITS
    ScopeManager
    0.49
    ագրություններ
    0.46
    RTLR
    0.45
    󠁢
    0.45
    probability
    0.44
     snippetHide
    0.44
    encodeWith
    0.44
    MCA
    0.43
     Probability
    0.43
    τια
    0.43
    Act Density 0.151%

    No Known Activations