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

    Neuronpedia

    INDEX
    Explanations

    qualities and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Whenever
    0.44
    Whenever
    0.41
    kov
    0.37
     erat
    0.33
     zodat
    0.33
    primarily
    0.32
    ="{
    0.32
     whenever
    0.31
     причем
    0.31
     lediglich
    0.31
    POSITIVE LOGITS
     considering
    0.51
     compared
    0.49
     paired
    0.46
    considering
    0.46
     estando
    0.45
     given
    0.45
     surrounded
    0.42
     going
    0.41
    skinned
    0.41
     combined
    0.40
    Act Density 0.063%

    No Known Activations