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

    Neuronpedia

    INDEX
    Explanations

    those seeking or experiencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.86
    ا
    1.84
    it
    1.63
    an
    1.59
     postérieures
    1.58
    u
    1.54
    uot
    1.52
    uh
    1.49
     postérieurs
    1.49
    ERT
    1.48
    POSITIVE LOGITS
    ০
    1.46
    ח
    1.36
    ний
    1.35
     وهذه
    1.33
    淇
    1.32
    ە
    1.31
    г
    1.27
    ný
    1.27
    ian
    1.24
    ी
    1.24
    Act Density 0.007%

    No Known Activations