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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fp
    -0.07
    CLS
    -0.07
     ›
    -0.07
    ipes
    -0.07
    極
    -0.06
     Sat
    -0.06
     Brands
    -0.06
     shoots
    -0.06
    "in
    -0.06
    &eacute
    -0.06
    POSITIVE LOGITS
     dobr
    0.06
     держ
    0.06
    英
    0.06
    _PRESS
    0.06
    _VEC
    0.06
     PvP
    0.06
    �
    0.06
    $route
    0.06
     poil
    0.06
     зада
    0.06
    Act Density 0.001%

    No Known Activations