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

    Neuronpedia

    INDEX
    Explanations

    rop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acquisition
    -0.07
    -neck
    -0.07
     tanks
    -0.06
    (sol
    -0.06
    -caption
    -0.06
     sandy
    -0.06
    校
    -0.06
     leather
    -0.06
     ($("#
    -0.06
     laid
    -0.06
    POSITIVE LOGITS
     explosives
    0.06
     Toledo
    0.06
     apro
    0.06
    ีย
    0.06
    orry
    0.06
     VERBOSE
    0.06
    ++;
    0.06
    ческий
    0.06
     آنلاین
    0.06
    년
    0.06
    Act Density 0.001%

    No Known Activations