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

    Neuronpedia

    INDEX
    Explanations

    Park

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extremism
    -0.07
     μπ
    -0.07
    obo
    -0.06
    MLS
    -0.06
    ою
    -0.06
    .fp
    -0.06
     rq
    -0.06
     assignments
    -0.06
     Grupo
    -0.06
    party
    -0.06
    POSITIVE LOGITS
    ثل
    0.07
     AXIS
    0.06
    ales
    0.06
    olist
    0.06
    =format
    0.06
     appeared
    0.06
    -modules
    0.06
     rarity
    0.06
    isify
    0.06
     Reader
    0.06
    Act Density 0.046%

    No Known Activations