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

    Neuronpedia

    INDEX
    Explanations

    Technical subjects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.87
    SharedDtor
    -0.83
     الرياضيه
    -0.81
    ėk
    -0.80
    CodedInputStream
    -0.79
    Cyfeiriadau
    -0.78
    writeFieldEnd
    -0.76
    LookAnd
    -0.74
     NSCoder
    -0.73
    
    -0.72
    POSITIVE LOGITS
    ste
    0.39
     ste
    0.39
    spin
    0.38
     doInBackground
    0.35
    Xna
    0.34
    CO
    0.33
     ster
    0.32
     spin
    0.32
     st
    0.31
    stan
    0.31
    Act Density 0.003%

    No Known Activations