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

    Neuronpedia

    INDEX
    Explanations

    Arrow symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	cancel
    -0.06
    .Unmarshal
    -0.06
    pon
    -0.06
    全国
    -0.06
    bak
    -0.06
    ViewSet
    -0.06
     Conexion
    -0.06
     negativity
    -0.06
    .mvp
    -0.06
    ýš
    -0.06
    POSITIVE LOGITS
     discard
    0.07
     amen
    0.06
     stood
    0.06
    leared
    0.06
     Δι
    0.06
     bedroom
    0.06
    chunks
    0.06
     modern
    0.06
    ��
    0.06
     wedding
    0.06
    Act Density 0.015%

    No Known Activations