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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelRenderer
    -0.07
     马
    -0.06
     demanded
    -0.06
    ponent
    -0.06
    pm
    -0.06
    'B
    -0.06
     (${
    -0.06
    _third
    -0.06
    _train
    -0.06
     أكثر
    -0.06
    POSITIVE LOGITS
    ￣
    0.07
    ovice
    0.06
    NSIndexPath
    0.06
    .'.$
    0.06
     AppState
    0.06
    σή
    0.06
     proletariat
    0.06
    -important
    0.06
    piry
    0.06
     เขต
    0.06
    Act Density 0.000%

    No Known Activations