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

    Neuronpedia

    INDEX
    Explanations

    Email generation/rewriting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الف
    -0.08
     이야
    -0.08
    quial
    -0.07
     THE
    -0.07
     Ա
    -0.07
    Normalization
    -0.07
    _frag
    -0.07
    һә
    -0.07
    豆
    -0.07
    Nou
    -0.07
    POSITIVE LOGITS
    0.08
     colleg
    0.08
     защищ
    0.08
     Hoog
    0.07
     ouverts
    0.07
     принимать
    0.07
     verhu
    0.07
     соедин
    0.07
     colon
    0.07
     landlord
    0.07
    Act Density 0.002%
    No Known Activations