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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .checked
    -0.07
    ographed
    -0.06
     Vend
    -0.06
    �
    -0.06
     skewed
    -0.06
    NB
    -0.06
    FileSync
    -0.06
    venida
    -0.06
    _remove
    -0.06
    exchange
    -0.06
    POSITIVE LOGITS
    _codegen
    0.07
     položky
    0.06
    /io
    0.06
     leží
    0.06
     meant
    0.06
    )object
    0.06
    .М
    0.06
     ((*
    0.06
    اوه
    0.06
     míst
    0.06
    Act Density 0.025%

    No Known Activations