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

    Neuronpedia

    INDEX
    Explanations

    —

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stery
    -0.07
    Š
    -0.06
     Snape
    -0.06
    इन
    -0.06
     nes
    -0.06
    Italic
    -0.06
     بيت
    -0.06
    gien
    -0.06
    �
    -0.06
    üm
    -0.06
    POSITIVE LOGITS
    	width
    0.07
     Preservation
    0.07
    remove
    0.07
     Wouldn
    0.07
    hopefully
    0.06
     liable
    0.06
     preservation
    0.06
    ToAdd
    0.06
    dashboard
    0.06
     restoration
    0.06
    Act Density 0.000%

    No Known Activations