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

    Neuronpedia

    INDEX
    Explanations

    synthetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (defun
    -0.06
    vím
    -0.06
    το
    -0.06
     Originally
    -0.06
    otros
    -0.06
    idebar
    -0.06
    (defvar
    -0.06
    umann
    -0.06
    opacity
    -0.06
     ул
    -0.06
    POSITIVE LOGITS
     staunch
    0.08
     servings
    0.08
    Flow
    0.07
     OSS
    0.07
     kö
    0.07
    Yep
    0.07
     extremes
    0.07
    Activate
    0.06
    .concat
    0.06
    _matrix
    0.06
    Act Density 0.005%

    No Known Activations