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

    Neuronpedia

    INDEX
    Explanations

    dean followed by name or title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    1.59
    daki
    1.39
    ной
    1.38
    t
    1.36
    ด
    1.31
    ě
    1.30
    きた
    1.26
    l
    1.22
    dı
    1.17
     hasn
    1.13
    POSITIVE LOGITS
    ates
    1.27
    ح
    1.22
    itation
    1.21
    س
    1.20
    jection
    1.10
    aching
    1.01
    ancies
    1.01
    сів
    1.01
    uster
    1.00
    quist
    1.00
    Act Density 0.001%

    No Known Activations