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

    Neuronpedia

    INDEX
    Explanations

    CR

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seab
    -0.08
    роме
    -0.07
    getPost
    -0.07
     tab
    -0.07
    ватися
    -0.07
    应该
    -0.07
     getMessage
    -0.07
    ichTextBox
    -0.07
    istringstream
    -0.07
     abide
    -0.06
    POSITIVE LOGITS
    (cr
    0.07
    Cr
    0.06
     crackers
    0.06
    컨
    0.06
     trail
    0.06
    Pl
    0.06
    cr
    0.06
    PM
    0.06
     Crowley
    0.06
    run
    0.06
    Act Density 0.008%

    No Known Activations