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

    Neuronpedia

    INDEX
    Explanations

    Separating text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     focused
    -0.08
    ncpy
    -0.08
     pictured
    -0.08
     మార్క
    -0.07
    衡
    -0.07
    solute
    -0.07
     iconic
    -0.07
     embl
    -0.07
     limit
    -0.07
    市场
    -0.07
    POSITIVE LOGITS
     мед
    0.09
     начинают
    0.08
     Fakult
    0.08
    ોર
    0.08
     userdata
    0.08
     analsex
    0.08
     fakult
    0.08
    část
    0.08
    густ
    0.08
     последователь
    0.08
    Act Density 0.108%

    No Known Activations