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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fk
    -0.06
    ザ
    -0.06
     Б
    -0.06
    hev
    -0.06
    ib
    -0.06
     Alto
    -0.06
     manageable
    -0.06
     lesbische
    -0.06
     mant
    -0.06
    蛇
    -0.06
    POSITIVE LOGITS
    malink
    0.07
     {.
    0.07
     abortions
    0.07
     ResultSet
    0.07
     Brewing
    0.07
    0.06
     Sail
    0.06
    انون
    0.06
     ром
    0.06
    =device
    0.06
    Act Density 0.036%

    No Known Activations