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

    Neuronpedia

    INDEX
    Explanations

    Toxic relationships/behaviors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ूस
    -0.07
    ighton
    -0.07
     coatings
    -0.07
     prolific
    -0.07
    カー
    -0.07
    yield
    -0.07
    _combined
    -0.06
    IELD
    -0.06
    $fields
    -0.06
    lp
    -0.06
    POSITIVE LOGITS
     função
    0.06
     initView
    0.06
     Ney
    0.06
    .RequestMethod
    0.06
     affid
    0.05
    838
    0.05
     Affordable
    0.05
    .StartPosition
    0.05
     Jaime
    0.05
    .Msg
    0.05
    Act Density 0.039%

    No Known Activations