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

    Neuronpedia

    INDEX
    Explanations

    lab results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pathlib
    -0.06
     '{}'
    -0.06
     Mitarbeiter
    -0.06
    .AllArgsConstructor
    -0.06
    Josh
    -0.06
     proj
    -0.06
    Guide
    -0.06
    _Source
    -0.06
    ̣c
    -0.05
    =['
    -0.05
    POSITIVE LOGITS
    .undefined
    0.07
     Mans
    0.07
     demonstration
    0.06
     peu
    0.06
    ccording
    0.06
    破
    0.06
    olithic
    0.06
     forks
    0.06
     objc
    0.06
     Support
    0.06
    Act Density 0.019%

    No Known Activations