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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ib
    -0.07
    (ld
    -0.07
    _AV
    -0.07
     passenger
    -0.07
    布
    -0.07
    Downloading
    -0.07
    جر
    -0.06
    lass
    -0.06
    olley
    -0.06
    Record
    -0.06
    POSITIVE LOGITS
     succes
    0.06
     Eagles
    0.06
    alignment
    0.06
     extraordinarily
    0.06
    :this
    0.06
    .atan
    0.06
    	sl
    0.06
     energies
    0.06
     debunk
    0.06
     اهم
    0.06
    Act Density 0.016%

    No Known Activations