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

    Neuronpedia

    INDEX
    Explanations

    wrapper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liž
    -0.07
     zien
    -0.06
     bilin
    -0.06
     criar
    -0.06
     rl
    -0.06
    LR
    -0.06
    umbotron
    -0.06
     cob
    -0.06
     pipeline
    -0.06
    .rl
    -0.06
    POSITIVE LOGITS
    >xpath
    0.07
     altında
    0.07
    ****/↵
    0.06
     Athletic
    0.06
     spoof
    0.06
    |()↵
    0.06
    %=
    0.06
     [],
↵
    0.06
    Local
    0.06
     ασ
    0.06
    Act Density 0.001%

    No Known Activations