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

    Neuronpedia

    INDEX
    Explanations

    Protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivant
    -0.07
    jekt
    -0.06
     unemployed
    -0.06
    θούν
    -0.06
     сп
    -0.06
    -lines
    -0.06
    oop
    -0.06
    _vars
    -0.06
    ip
    -0.06
    .TABLE
    -0.06
    POSITIVE LOGITS
     Protection
    0.15
     protection
    0.08
     clen
    0.07
    TECTION
    0.07
    르게
    0.07
    주
    0.07
    」と
    0.07
     заклад
    0.07
     getSupportActionBar
    0.07
     tarea
    0.06
    Act Density 0.001%

    No Known Activations