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

    Neuronpedia

    INDEX
    Explanations

    max

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کرنا
    0.35
     distort
    0.35
    埬
    0.35
     Bereich
    0.34
    ವರು
    0.33
     inve
    0.33
    을
    0.33
    頨
    0.32
     ל
    0.32
     иска
    0.31
    POSITIVE LOGITS
     wundersch
    0.36
    alkyl
    0.35
    íss
    0.34
    acterial
    0.34
    alámb
    0.33
    пах
    0.31
    ampoo
    0.31
    ច្រើន
    0.31
     +
    0.31
    asshi
    0.30
    Act Density 0.001%

    No Known Activations