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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SOME
    -0.07
    dyn
    -0.07
     quelque
    -0.07
    ряду
    -0.06
     wann
    -0.06
    Counts
    -0.06
    _CONFIGURATION
    -0.06
     raped
    -0.06
    madığı
    -0.06
     Equation
    -0.06
    POSITIVE LOGITS
     emulate
    0.06
     unpleasant
    0.06
    (paths
    0.06
     Inspector
    0.06
    GGLE
    0.06
     hf
    0.06
     біл
    0.06
    علی
    0.06
    omm
    0.05
    .Mouse
    0.05
    Act Density 0.016%

    No Known Activations