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

    Neuronpedia

    INDEX
    Explanations

    feasibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ccount
    -0.07
    ibold
    -0.07
    PIO
    -0.07
     deaths
    -0.07
    umericUpDown
    -0.07
    рад
    -0.07
     typing
    -0.06
     piano
    -0.06
     words
    -0.06
    uros
    -0.06
    POSITIVE LOGITS
     feasible
    0.15
     feasibility
    0.12
    feas
    0.09
     feas
    0.09
    _remain
    0.08
    can
    0.07
    ESA
    0.07
     Freedom
    0.07
    _ln
    0.06
    Java
    0.06
    Act Density 0.004%

    No Known Activations