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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]!='
    -0.07
    '][]
    -0.07
    ጽ
    -0.07
    还不
    -0.06
     mystery
    -0.06
    nings
    -0.06
     Bet
    -0.06
     uncomp
    -0.06
    ⬛
    -0.06
     Assuming
    -0.06
    POSITIVE LOGITS
     dijo
    0.08
     presidente
    0.07
    irá
    0.07
    -head
    0.07
     largo
    0.07
    avigate
    0.06
     quiero
    0.06
    aba
    0.06
    ';
↵
    0.06
    lia
    0.06
    Act Density 0.002%

    No Known Activations