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

    Neuronpedia

    INDEX
    Explanations

    rel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parents
    -0.08
     jButton
    -0.07
     aloud
    -0.07
     reef
    -0.07
     informat
    -0.07
    MethodManager
    -0.07
     לעזור
    -0.07
     coordinating
    -0.07
    UTES
    -0.06
    ちょうど
    -0.06
    POSITIVE LOGITS
     adoles
    0.07
     пери
    0.07
    撼
    0.07
    ą
    0.06
    生存
    0.06
     quarterly
    0.06
    ológica
    0.06
    时段
    0.06
    된
    0.06
    _RING
    0.06
    Act Density 0.001%

    No Known Activations