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

    Neuronpedia

    INDEX
    Explanations

    application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    40
    -0.08
    45
    -0.07
     cast
    -0.07
    85
    -0.07
    87
    -0.06
    12
    -0.06
     precise
    -0.06
    83
    -0.06
    192
    -0.06
     có
    -0.06
    POSITIVE LOGITS
    application
    0.08
    HAM
    0.08
    ?><?
    0.07
    LOSS
    0.07
    ?><
    0.07
     APPLICATION
    0.07
    .Reflection
    0.07
     паци
    0.07
    applications
    0.07
    >tag
    0.07
    Act Density 0.040%

    No Known Activations