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

    Neuronpedia

    INDEX
    Explanations

    Tournament results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cabin
    -0.07
     açıklam
    -0.07
     nir
    -0.07
     Asia
    -0.06
     Asian
    -0.06
     Irish
    -0.06
     mike
    -0.06
    Charles
    -0.06
     towers
    -0.06
    Ford
    -0.06
    POSITIVE LOGITS
    Magnitude
    0.07
    \F
    0.06
    .scrollView
    0.06
    lopen
    0.06
    силь
    0.06
     psychologically
    0.06
     revamped
    0.06
    tolist
    0.06
    *>(
    0.06
    .constants
    0.06
    Act Density 0.011%

    No Known Activations