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

    Neuronpedia

    INDEX
    Explanations

    km

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cross
    -0.08
    _numeric
    -0.08
     Chavez
    -0.08
     Chest
    -0.07
     Scoped
    -0.07
     kles
    -0.07
     Checker
    -0.07
     Glass
    -0.07
     karş
    -0.07
     undergo
    -0.06
    POSITIVE LOGITS
     Vs
    0.07
    nič
    0.06
     Coupon
    0.06
    etically
    0.06
    cepts
    0.06
     [~,
    0.06
     failures
    0.06
     Also
    0.06
     "));↵
    0.05
    аны
    0.05
    Act Density 0.012%

    No Known Activations