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

    Neuronpedia

    INDEX
    Explanations

    plates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Locked
    -0.07
    ubits
    -0.07
    _codes
    -0.06
     puede
    -0.06
     project
    -0.06
     Plaint
    -0.06
    716
    -0.06
     graphite
    -0.06
    CELL
    -0.06
     rebell
    -0.06
    POSITIVE LOGITS
     کنید
    0.07
     cmb
    0.06
     світ
    0.06
    таки
    0.06
     Rpc
    0.06
     frauen
    0.06
    	opts
    0.06
    остью
    0.06
    .listdir
    0.06
    .This
    0.06
    Act Density 0.016%

    No Known Activations