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

    Neuronpedia

    INDEX
    Explanations

    requirements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approved
    -0.07
     Seth
    -0.07
    “At
    -0.06
    ENSION
    -0.06
    Paint
    -0.06
    =yes
    -0.06
     �
    -0.06
    行動
    -0.06
    -UA
    -0.06
    _days
    -0.06
    POSITIVE LOGITS
     sideways
    0.07
    -regexp
    0.06
    :numel
    0.06
     sheriff
    0.06
    berapa
    0.06
     Classe
    0.06
    qq
    0.06
     cuer
    0.06
    �
    0.06
    �
    0.06
    Act Density 0.026%

    No Known Activations