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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -card
    -0.07
     Dr
    -0.07
     FileAccess
    -0.07
     lent
    -0.07
     flirt
    -0.07
    _INTERNAL
    -0.07
     lacks
    -0.06
    cms
    -0.06
    /User
    -0.06
    xc
    -0.06
    POSITIVE LOGITS
    ":[{"
    0.06
    placeholders
    0.06
     Projection
    0.06
     contentValues
    0.06
    othy
    0.06
     ',↵
    0.06
    }()↵
    0.06
    .assertAlmostEqual
    0.06
    па
    0.06
    flatten
    0.06
    Act Density 0.029%

    No Known Activations