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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    670
    -0.07
     hai
    -0.07
    .compiler
    -0.06
    StatusCode
    -0.06
     wür
    -0.06
    úmeros
    -0.06
     UINT
    -0.06
    UGINS
    -0.06
     ficken
    -0.06
    strike
    -0.06
    POSITIVE LOGITS
     Space
    0.07
    Space
    0.06
     ally
    0.06
    ोल
    0.06
     christmas
    0.06
    的事
    0.06
    lld
    0.06
    新闻
    0.06
     Ents
    0.06
    Arch
    0.06
    Act Density 0.006%

    No Known Activations