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

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Meet
    -0.07
     Betty
    -0.07
    彩
    -0.07
    cout
    -0.07
     What
    -0.07
     THEIR
    -0.07
     Tam
    -0.07
     My
    -0.06
    הת
    -0.06
    不见
    -0.06
    POSITIVE LOGITS
    _mtx
    0.09
    _draft
    0.08
    包容
    0.07
    わか
    0.07
     incarcerated
    0.07
    쨍
    0.07
     сез
    0.07
    选址
    0.07
     soaking
    0.07
    노동
    0.07
    Act Density 0.009%

    No Known Activations