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

    Neuronpedia

    INDEX
    Explanations

    initial API and implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    breitung
    -0.84
    važ
    -0.82
     entrepreneurs
    -0.79
    わない
    -0.77
    média
    -0.77
     runny
    -0.77
    プレス
    -0.76
    žiai
    -0.75
    inição
    -0.73
     ciertamente
    -0.72
    POSITIVE LOGITS
     initial
    1.30
     changes
    1.12
     Initial
    1.06
    Initial
    1.02
    initial
    0.98
    初始
    0.98
    aptation
    0.96
    setInitial
    0.95
     podstawie
    0.95
    ㅇ
    0.92
    Act Density 0.043%

    No Known Activations