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

    Neuronpedia

    INDEX
    Explanations

    C's response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Noeud
    0.52
    VENTION
    0.49
    waffe
    0.49
    猀
    0.48
     Wiss
    0.45
    lé
    0.44
     Bele
    0.44
     Hochsch
    0.43
    ланы
    0.43
     Lesen
    0.43
    POSITIVE LOGITS
    c
    0.55
    r
    0.51
    Section
    0.48
    ig
    0.46
    2
    0.45
    5
    0.45
    1
    0.43
    b
    0.43
    g
    0.42
    6
    0.42
    Act Density 0.002%

    No Known Activations