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

    Neuronpedia

    INDEX
    Explanations

    programming utilities and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ங்களே
    0.33
     আর্থ
    0.33
    レタン
    0.32
    রাস
    0.31
     வெளியாக
    0.31
    /\/
    0.31
    áce
    0.31
    ântul
    0.30
    helial
    0.30
     ASC
    0.30
    POSITIVE LOGITS
    utils
    0.73
    exceptions
    0.67
     utils
    0.66
     exceptions
    0.63
    exception
    0.59
    Utils
    0.58
    Exceptions
    0.57
    model
    0.57
    services
    0.56
     util
    0.56
    Act Density 0.002%

    No Known Activations