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

    Neuronpedia

    INDEX
    Explanations

    reeze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iT
    -0.06
     lbl
    -0.06
    196
    -0.06
    :nil
    -0.06
    .lst
    -0.06
    erator
    -0.06
    _control
    -0.06
    location
    -0.06
    _widgets
    -0.05
    757
    -0.05
    POSITIVE LOGITS
     hepsi
    0.08
    iveness
    0.07
     tactile
    0.07
    exist
    0.07
    (strategy
    0.07
    _trade
    0.07
    正式
    0.07
    rome
    0.07
     nrows
    0.07
     구글상위
    0.07
    Act Density 0.343%

    No Known Activations