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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cortex
    -0.08
     esp
    -0.06
     bac
    -0.06
     manipulated
    -0.06
     Aviv
    -0.06
    attacks
    -0.06
     replicated
    -0.06
     revision
    -0.06
    acency
    -0.06
    throat
    -0.06
    POSITIVE LOGITS
     времен
    0.07
    .clips
    0.07
    عت
    0.07
     []↵
    0.06
    РО
    0.06
     QStringList
    0.06
    	NdrFcShort
    0.06
    (SK
    0.06
    League
    0.06
    kind
    0.06
    Act Density 0.001%

    No Known Activations