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

    Neuronpedia

    INDEX
    Explanations

    formerly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strip
    -0.92
    formerly
    -0.90
     strip
    -0.86
     rumors
    -0.84
     Strips
    -0.81
    Strip
    -0.79
     strips
    -0.79
     rumor
    -0.77
     formerly
    -0.76
    Formerly
    -0.74
    POSITIVE LOGITS
    RegressionTest
    0.90
     protoimpl
    0.65
     propOrder
    0.64
    CloseOperation
    0.63
     Bret
    0.61
    ]--;
    0.61
    estival
    0.58
    LookAnd
    0.58
     ModelExpression
    0.58
    omeness
    0.57
    Act Density 0.140%

    No Known Activations