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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compos
    -0.07
     highlight
    -0.07
    Forest
    -0.07
    choice
    -0.07
    زی
    -0.07
    -dropdown
    -0.07
    Inst
    -0.07
    Tonight
    -0.06
     pillars
    -0.06
     Defensive
    -0.06
    POSITIVE LOGITS
    _journal
    0.07
    *dt
    0.07
     الحديث
    0.07
     yana
    0.07
    .canvas
    0.07
    専
    0.06
    .sum
    0.06
    .norm
    0.06
    .Summary
    0.06
     léka
    0.06
    Act Density 0.023%

    No Known Activations