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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubbo
    -0.06
    adows
    -0.06
    とも
    -0.06
    ovali
    -0.06
     luder
    -0.06
    渡
    -0.06
     typu
    -0.06
    goods
    -0.06
    lds
    -0.06
    ;b
    -0.06
    POSITIVE LOGITS
     EXAMPLE
    0.07
     dodge
    0.07
    搜
    0.06
    =↵
    0.06
    REMOTE
    0.06
     Yam
    0.06
     RIGHT
    0.06
     deductions
    0.06
     BMW
    0.06
     Prevent
    0.06
    Act Density 0.000%

    No Known Activations