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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lp
    -0.07
    opsy
    -0.06
    آم
    -0.06
    andi
    -0.06
     IOError
    -0.06
    Util
    -0.06
    �
    -0.06
     mer
    -0.05
     {},
    -0.05
    Descripcion
    -0.05
    POSITIVE LOGITS
     hitting
    0.07
     whether
    0.07
    ابعة
    0.07
     who
    0.07
     proving
    0.06
     Birleşik
    0.06
     surprisingly
    0.06
     timestep
    0.06
     ورد
    0.06
     veya
    0.06
    Act Density 0.002%

    No Known Activations