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

    Neuronpedia

    INDEX
    Explanations

    Proto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chosen
    -0.75
     legal
    -0.67
    chosen
    -0.66
     selected
    -0.66
     Chosen
    -0.58
     foregoing
    -0.56
    LEADING
    -0.53
    #+#
    -0.52
     Selected
    -0.51
    selected
    -0.51
    POSITIVE LOGITS
    BagLayout
    0.70
    tagHelperRunner
    0.65
     мәкал
    0.61
     Вікі
    0.60
    Vidite
    0.58
     combineReducers
    0.58
    ecap
    0.58
    clearTimeout
    0.57
    colgroup
    0.56
    inSlope
    0.55
    Act Density 0.076%

    No Known Activations