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

    Neuronpedia

    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Logging
    -0.07
    .Function
    -0.07
    renc
    -0.07
    POL
    -0.07
     NotImplemented
    -0.06
     outreach
    -0.06
    _CANNOT
    -0.06
    decoder
    -0.06
     Minds
    -0.06
     περί
    -0.06
    POSITIVE LOGITS
    險
    0.07
     tai
    0.06
     trọng
    0.06
     боли
    0.06
    DNA
    0.06
     chị
    0.06
    	glut
    0.06
    англ
    0.06
     balanced
    0.06
     янва
    0.06
    Act Density 0.000%

    No Known Activations