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

    Neuronpedia

    INDEX
    Explanations

    Alliteration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    바일
    -0.07
    —with
    -0.06
     تکن
    -0.06
     futile
    -0.06
    radan
    -0.06
     계획
    -0.06
     μου
    -0.06
    لمان
    -0.06
    料理
    -0.06
    โ
    -0.06
    POSITIVE LOGITS
    |:
    0.07
     jspb
    0.06
     ヾ
    0.06
    Technical
    0.06
     gymn
    0.06
    _BLEND
    0.06
    .reset
    0.06
     danger
    0.06
    善
    0.06
    .capacity
    0.06
    Act Density 0.014%

    No Known Activations