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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dude
    -0.07
    -sign
    -0.06
    -b
    -0.06
     members
    -0.06
     все
    -0.06
    -sale
    -0.06
     Trees
    -0.06
    られる
    -0.06
     wears
    -0.06
    -C
    -0.06
    POSITIVE LOGITS
     Anxiety
    0.07
    743
    0.07
    ALLOW
    0.07
    õi
    0.06
     Mojo
    0.06
    Experiment
    0.06
    .mid
    0.06
    produ
    0.06
     افز
    0.06
    окол
    0.06
    Act Density 0.020%

    No Known Activations