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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frosting
    -0.06
     landmark
    -0.06
     phá
    -0.06
     cca
    -0.06
     الول
    -0.06
    ")==
    -0.06
     metropolitan
    -0.06
     avenue
    -0.06
    .bulk
    -0.06
     grat
    -0.06
    POSITIVE LOGITS
     generally
    0.07
    ель
    0.07
     Pont
    0.06
    901
    0.06
    /T
    0.06
    来
    0.06
    ifton
    0.06
     Parse
    0.06
     technical
    0.06
    /V
    0.06
    Act Density 0.000%

    No Known Activations