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

    Neuronpedia

    INDEX
    Explanations

    ES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Feld
    -0.08
    .desc
    -0.07
    렵
    -0.07
    ник
    -0.07
    ,K
    -0.07
    Ross
    -0.07
    (SP
    -0.07
    _fg
    -0.07
     Alec
    -0.07
    úc
    -0.07
    POSITIVE LOGITS
    大厦
    0.07
    -sur
    0.07
    αι
    0.07
    .master
    0.07
     Outer
    0.07
     ORIGINAL
    0.07
    WAIT
    0.07
    larının
    0.07
    ORITY
    0.07
     đá
    0.07
    Act Density 0.000%

    No Known Activations