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

    Neuronpedia

    INDEX
    Explanations

    say [say or argue]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     інт
    -0.06
     bağ
    -0.06
     updater
    -0.06
     Honor
    -0.06
    	address
    -0.06
     ledger
    -0.06
     hậu
    -0.06
     Settlement
    -0.06
    _REFERER
    -0.06
     XVI
    -0.05
    POSITIVE LOGITS
    Suddenly
    0.07
    andid
    0.07
     Associated
    0.07
     Sul
    0.07
    cess
    0.07
    ({});↵
    0.07
    ogeneity
    0.07
     मश
    0.06
    _VAL
    0.06
    χεί
    0.06
    Act Density 0.160%

    No Known Activations