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

    Neuronpedia

    INDEX
    Explanations

    mnemonics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selenium
    -0.08
    timestamp
    -0.08
     timestamp
    -0.07
     hover
    -0.07
     stamping
    -0.07
     journal
    -0.07
    silver
    -0.07
     doj
    -0.07
    fp
    -0.07
     anonymity
    -0.07
    POSITIVE LOGITS
    口诀
    0.15
     remembered
    0.11
     memorize
    0.10
     mnemonic
    0.10
    牢记
    0.10
     remembering
    0.10
     aturan
    0.10
     纬
    0.10
     推荐
    0.09
     Memor
    0.09
    Act Density 0.013%

    No Known Activations