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

    Neuronpedia

    INDEX
    Explanations

    coding/HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     studied
    -0.07
    Rua
    -0.06
     în
    -0.06
    _file
    -0.06
    (visible
    -0.06
    -feedback
    -0.06
    rawn
    -0.06
    spender
    -0.06
     Rudd
    -0.06
    gee
    -0.06
    POSITIVE LOGITS
    ẩ
    0.07
    .middle
    0.06
    каж
    0.06
    ;
↵
↵
↵
↵
    0.06
     مص
    0.06
    �
    0.06
    Virgin
    0.06
     excluded
    0.06
    값
    0.06
    _grad
    0.06
    Act Density 0.100%

    No Known Activations