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

    Neuronpedia

    INDEX
    Explanations

    related to requests for assistance or proofs

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

    proof steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.60
     noDo
    -0.55
    ensement
    -0.53
    SerializedSize
    -0.53
     الرياضيه
    -0.51
    hoeddwyd
    -0.49
     înainte
    -0.47
    دانشنامهٔ
    -0.46
     ब्रेकडाउन
    -0.45
    Décès
    -0.45
    POSITIVE LOGITS
     steps
    0.96
    steps
    0.88
     step
    0.88
    Steps
    0.82
    step
    0.80
     Steps
    0.76
    STEPS
    0.73
     pasos
    0.72
    步骤
    0.69
    Step
    0.68
    Act Density 0.058%

    No Known Activations