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

    Neuronpedia

    INDEX
    Explanations

    hashing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dial
    -0.66
    IAL
    -0.65
     dial
    -0.63
    rano
    -0.63
    hash
    -0.62
    ی
    -0.62
    lake
    -0.61
     hash
    -0.60
    ibe
    -0.57
     hashing
    -0.57
    POSITIVE LOGITS
     themſelves
    0.72
    Havolalar
    0.66
     gddr
    0.66
    IntoConstraints
    0.64
     oxen
    0.63
     Efq
    0.63
    melons
    0.63
     Bacchus
    0.63
     Whigs
    0.62
     amphibians
    0.61
    Act Density 0.050%

    No Known Activations