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

    Neuronpedia

    INDEX
    Explanations

    return obj

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dring
    0.64
     dün
    0.56
    chtigen
    0.54
     médicaments
    0.53
     planen
    0.53
     Geräte
    0.51
    ného
    0.50
     både
    0.50
     längst
    0.50
     verhindert
    0.49
    POSITIVE LOGITS
    oda
    0.47
     may
    0.46
    Yay
    0.44
    ayah
    0.43
    idan
    0.42
     alternate
    0.41
    iro
    0.41
    DF
    0.40
    繭
    0.40
    oni
    0.39
    Act Density 0.000%

    No Known Activations