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

    Neuronpedia

    INDEX
    Explanations

    confidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MLP
    -0.06
     updatedAt
    -0.06
    _ASC
    -0.06
     phương
    -0.06
     carrot
    -0.06
    Gap
    -0.06
    akeFromNib
    -0.06
     Analyzer
    -0.06
    .measure
    -0.06
     fire
    -0.06
    POSITIVE LOGITS
    omm
    0.07
     whether
    0.07
    criptions
    0.07
    backgroundColor
    0.07
    лися
    0.06
     precisely
    0.06
    Installing
    0.06
     galaxies
    0.06
     locating
    0.06
     vv
    0.06
    Act Density 0.004%

    No Known Activations