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

    Neuronpedia

    INDEX
    Explanations

    writing definitive or specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ವಿಧ
    0.36
    Durch
    0.34
     stanje
    0.34
    ).</
    0.33
     ойноо
    0.33
     výrob
    0.32
     gjøre
    0.32
    UsedError
    0.32
     जाण
    0.31
    年的
    0.31
    POSITIVE LOGITS
    y
    0.63
    ar
    0.55
    el
    0.54
    i
    0.52
    e
    0.50
    al
    0.48
     I
    0.46
    P
    0.45
     P
    0.44
    en
    0.44
    Act Density 0.726%

    No Known Activations