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

    Neuronpedia

    INDEX
    Explanations

    questions beginning with "how," "what," or "why."

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

    how or what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.46
     Rogan
    -0.45
    Portail
    -0.45
    "]));
    -0.43
    makeText
    -0.42
     Rosalie
    -0.42
    posedge
    -0.41
    "])){
    -0.41
    '])){
    -0.41
    twimg
    -0.41
    POSITIVE LOGITS
    IVEREF
    0.45
    hilangan
    0.43
     invokingState
    0.42
    Портали
    0.41
    ErrUnexpected
    0.40
     leaſt
    0.39
     relève
    0.39
    0.38
    olidation
    0.38
    hyrchwyd
    0.38
    Act Density 0.051%

    No Known Activations