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

    Neuronpedia

    INDEX
    Explanations

    technical terms and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ្ត
    0.64
    ">*
    0.64
     цифро
    0.64
    VISIONS
    0.64
    roduction
    0.63
     grudnia
    0.63
     полноцен
    0.63
    Instructions
    0.63
    нет
    0.62
    unavailable
    0.62
    POSITIVE LOGITS
     její
    0.64
     aware
    0.62
     those
    0.59
     preferentially
    0.59
     prefer
    0.57
     matching
    0.57
     preferential
    0.57
     Cab
    0.57
     jejich
    0.56
     Match
    0.56
    Act Density 0.558%

    No Known Activations