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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ind
    -0.07
    ERO
    -0.06
     recap
    -0.06
     aromatic
    -0.06
    _flutter
    -0.06
     Portfolio
    -0.06
     purse
    -0.06
    _ip
    -0.06
    ,title
    -0.06
    ailer
    -0.06
    POSITIVE LOGITS
     dib
    0.07
     önünde
    0.07
    Vel
    0.07
    .param
    0.06
    .TypeString
    0.06
     nossa
    0.06
     acknow
    0.06
    .timeScale
    0.06
    .matrix
    0.06
     prejudices
    0.06
    Act Density 0.057%

    No Known Activations