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

    Neuronpedia

    INDEX
    Explanations

    warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ל
    -0.06
    _click
    -0.06
    ubb
    -0.06
     اول
    -0.06
    Decrypt
    -0.06
    Lean
    -0.06
    하나
    -0.06
    Backup
    -0.06
    )!=
    -0.06
    _long
    -0.05
    POSITIVE LOGITS
    Arn
    0.07
    (dirname
    0.06
     urb
    0.06
    _nonce
    0.06
     Coch
    0.06
     serde
    0.06
    licable
    0.06
     anche
    0.06
     advertisement
    0.06
     poses
    0.06
    Act Density 0.006%

    No Known Activations