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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _simple
    -0.07
    uptools
    -0.06
     Cres
    -0.06
     sociedad
    -0.06
     generator
    -0.06
    격
    -0.06
    istributor
    -0.06
    693
    -0.06
     DataView
    -0.06
    CHandle
    -0.06
    POSITIVE LOGITS
    стоя
    0.07
     assigning
    0.07
    !.
    0.06
     Tiếng
    0.06
    ją
    0.06
     prejudices
    0.06
    !!.
    0.06
     RT
    0.06
    ig
    0.06
     REPLACE
    0.06
    Act Density 0.108%

    No Known Activations