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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     departments
    -0.07
     Get
    -0.07
     cualquier
    -0.06
     Mafia
    -0.06
     Dimension
    -0.06
     awful
    -0.06
     LOCATION
    -0.06
    gren
    -0.06
    GLE
    -0.06
     làm
    -0.06
    POSITIVE LOGITS
    _Private
    0.08
     harass
    0.07
     قابل
    0.06
     RandomForest
    0.06
    entially
    0.06
    establish
    0.06
    lüğ
    0.06
    _mask
    0.06
    _expect
    0.06
    peaker
    0.06
    Act Density 0.047%

    No Known Activations