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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.52
     I
    -0.45
     called
    -0.45
     displayed
    -0.43
     couldn
    -0.43
     was
    -0.41
     tỏ
    -0.41
     heard
    -0.41
     stood
    -0.40
     used
    -0.39
    POSITIVE LOGITS
    脚注の使い方
    0.80
    .}\
    0.79
     intptr
    0.75
    Према
    0.74
    ConstraintMaker
    0.73
    ſelves
    0.71
    ſelf
    0.71
    èdia
    0.69
    etheless
    0.66
    .}}
    0.65
    Act Density 0.002%

    No Known Activations