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

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.08
    겜
    -0.07
    割
    -0.07
    ily
    -0.07
    GRE
    -0.07
    _PR
    -0.06
    涉
    -0.06
    吞噬
    -0.06
    牵
    -0.06
     lent
    -0.06
    POSITIVE LOGITS
     success
    0.09
     Success
    0.08
    (push
    0.08
     managers
    0.07
    -designed
    0.07
    -established
    0.07
     bezpośredni
    0.07
     transition
    0.07
    Successful
    0.07
    .Login
    0.07
    Act Density 0.039%

    No Known Activations