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

    Neuronpedia

    INDEX
    Explanations

    host

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     контроль
    -0.08
    ्रमण
    -0.07
    _grid
    -0.07
    �
    -0.07
    _inner
    -0.07
     stats
    -0.06
    ncmp
    -0.06
    $p
    -0.06
    semb
    -0.06
    ýv
    -0.06
    POSITIVE LOGITS
     serait
    0.07
    izen
    0.07
     January
    0.07
     cre
    0.07
     Derby
    0.07
    ANDING
    0.07
     eternity
    0.07
     {}
    0.06
     murderer
    0.06
     culinary
    0.06
    Act Density 0.572%

    No Known Activations