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

    Neuronpedia

    INDEX
    Explanations

    Arc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خد
    -0.08
    adí
    -0.07
     vede
    -0.06
    .springframework
    -0.06
     feeling
    -0.06
     pitcher
    -0.06
    ака
    -0.06
     因
    -0.06
    只要
    -0.06
    災
    -0.06
    POSITIVE LOGITS
    assword
    0.07
    our
    0.07
     BCH
    0.07
     rolls
    0.07
     Recognition
    0.07
    issions
    0.07
    _plate
    0.06
    Deleting
    0.06
     onPostExecute
    0.06
    	constructor
    0.06
    Act Density 0.002%

    No Known Activations