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

    Neuronpedia

    INDEX
    Explanations

    code or mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ribbon
    -0.06
     wide
    -0.06
    855
    -0.06
    _ROM
    -0.06
    -carousel
    -0.05
    Prov
    -0.05
    irror
    -0.05
     tmpl
    -0.05
    ullan
    -0.05
    -theme
    -0.05
    POSITIVE LOGITS
     departing
    0.07
    ImageView
    0.07
     "[
    0.07
     Lucky
    0.07
     speeding
    0.07
    JOB
    0.07
    父亲
    0.07
     disappointment
    0.07
     assemble
    0.07
    鳥
    0.06
    Act Density 0.000%

    No Known Activations