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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PU
    -0.06
    ीं,
    -0.06
    ini
    -0.06
    cyan
    -0.06
    lingen
    -0.06
     obligatory
    -0.06
    usive
    -0.06
    drawing
    -0.06
    amientos
    -0.06
    -Free
    -0.06
    POSITIVE LOGITS
     baktı
    0.08
     후보
    0.08
     obsahuje
    0.07
    _EXPR
    0.07
     переж
    0.07
    &action
    0.07
     just
    0.07
     pocit
    0.06
    (IService
    0.06
    (job
    0.06
    Act Density 0.012%

    No Known Activations