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

    Neuronpedia

    INDEX
    Explanations

    Returns: None

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BV
    0.38
    PIRED
    0.38
    dried
    0.37
    dry
    0.37
    헹
    0.37
    CORD
    0.36
    IRED
    0.36
    neutrophiles
    0.36
    KBr
    0.36
    lardır
    0.36
    POSITIVE LOGITS
     Assy
    0.46
     positives
    0.45
     hope
    0.44
     closely
    0.43
     bisa
    0.42
     zu
    0.42
     appease
    0.42
     values
    0.41
     brav
    0.41
     Ch
    0.41
    Act Density 0.033%

    No Known Activations