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

    Neuronpedia

    INDEX
    Explanations

    stability/durability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '~/
    -0.07
     memberId
    -0.07
     collo
    -0.07
    \Carbon
    -0.06
    mişti
    -0.06
     Zeit
    -0.06
    دی
    -0.06
    _KEY
    -0.06
    .reg
    -0.06
    .dequeueReusableCell
    -0.06
    POSITIVE LOGITS
     storyline
    0.06
    ιν
    0.06
    warn
    0.06
    974
    0.06
     Beginning
    0.06
    ثر
    0.06
     stil
    0.05
    メント
    0.05
    entication
    0.05
    ุ
    0.05
    Act Density 0.009%

    No Known Activations