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

    Neuronpedia

    INDEX
    Explanations

    Walking on two legs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remedy
    -0.08
     Monter
    -0.07
     descriptive
    -0.07
    -volume
    -0.07
    ाया
    -0.07
     antid
    -0.07
     remed
    -0.07
     remedies
    -0.07
    \Helper
    -0.07
     insider
    -0.07
    POSITIVE LOGITS
    arrage
    0.09
     humains
    0.08
     duty
    0.08
    Duty
    0.08
     british
    0.08
    (bp
    0.08
     caminhada
    0.08
     gaw
    0.08
     глаза
    0.08
     pushes
    0.07
    Act Density 0.005%

    No Known Activations