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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quantitatively
    -0.79
     gynhyrchwyd
    -0.63
     qualitatively
    -0.63
     vaisseaux
    -0.63
     tiroirs
    -0.61
    spender
    -0.60
     Quantitative
    -0.60
    InjectAttribute
    -0.59
    hips
    -0.58
    bbene
    -0.58
    POSITIVE LOGITS
    DoubleQuotes
    0.56
     injustice
    0.47
     insanity
    0.46
     notice
    0.45
     recompense
    0.45
     metallurgy
    0.43
     monarchy
    0.43
     Queenstown
    0.42
    RTLD
    0.42
     AliExpress
    0.42
    Act Density 0.055%

    No Known Activations