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

    Neuronpedia

    INDEX
    Explanations

    ase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ---------
    -0.07
    ARGIN
    -0.06
     endangered
    -0.06
     Associ
    -0.06
    merchant
    -0.06
     chemin
    -0.06
     threats
    -0.06
     beneficiaries
    -0.06
    amente
    -0.06
    chsel
    -0.06
    POSITIVE LOGITS
    .dump
    0.07
    burst
    0.07
    rans
    0.07
    ש
    0.07
    ams
    0.06
    ushed
    0.06
     ASC
    0.06
     OAuth
    0.06
     senator
    0.06
     vak
    0.06
    Act Density 0.001%

    No Known Activations