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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     распрост
    -0.07
    Congratulations
    -0.07
     vouchers
    -0.07
     solicitud
    -0.07
    .DOWN
    -0.07
    _TEMPLATE
    -0.07
     jTable
    -0.07
    �
    -0.06
     feu
    -0.06
    这一天
    -0.06
    POSITIVE LOGITS
    ,
    0.11
    throp
    0.07
    形态
    0.07
     "\
    0.07
    xsd
    0.07
    нстру
    0.06
     Petsc
    0.06
    かも
    0.06
     multip
    0.06
    .
    0.06
    Act Density 0.002%

    No Known Activations