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

    Neuronpedia

    INDEX
    Explanations

    ov

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    šlo
    -0.08
     rady
    -0.07
     SCE
    -0.06
     страны
    -0.06
     요청
    -0.06
    ,it
    -0.06
     więcej
    -0.06
    _cr
    -0.06
     bật
    -0.06
    kové
    -0.06
    POSITIVE LOGITS
     Alexis
    0.07
     Enemy
    0.07
    (Function
    0.07
     converged
    0.06
    .et
    0.06
    俺は
    0.06
     Fat
    0.06
    olin
    0.06
    .undefined
    0.06
     Char
    0.06
    Act Density 0.239%

    No Known Activations