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

    Neuronpedia

    INDEX
    Explanations

    location/territory descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fl
    -0.08
    WAY
    -0.07
    atholic
    -0.07
    TabPage
    -0.07
     podnikatel
    -0.07
    备注
    -0.07
    _mac
    -0.06
    (prediction
    -0.06
    .MessageBox
    -0.06
     располаг
    -0.06
    POSITIVE LOGITS
     alter
    0.06
     reign
    0.06
     aprender
    0.06
     collide
    0.06
     snapped
    0.06
    acts
    0.06
    slide
    0.06
     slowed
    0.06
    :`
    0.06
    บบ
    0.05
    Act Density 0.128%

    No Known Activations