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

    Neuronpedia

    INDEX
    Explanations

    mathematical matrices and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Conditioning
    0.59
     conditioned
    0.58
    conditioning
    0.56
     конди
    0.55
     condicion
    0.54
     conditioning
    0.53
     conclu
    0.46
    conditioned
    0.45
    lexeme
    0.41
     Fili
    0.41
    POSITIVE LOGITS
    压
    0.46
    trasound
    0.43
    irical
    0.40
     wolf
    0.40
    ATIVE
    0.39
    agonal
    0.37
    ূর
    0.37
    endish
    0.37
    rivial
    0.37
    Engel
    0.36
    Act Density 0.002%

    No Known Activations