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

    Neuronpedia

    INDEX
    Explanations

    `USING` clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UniqueIdentifier
    0.44
    ネート
    0.40
     १५
    0.38
    )\}$
    0.38
     heures
    0.38
     übrigens
    0.37
    ).\
    0.37
    ᅵ
    0.36
     pupils
    0.36
     lĩnh
    0.36
    POSITIVE LOGITS
    ikka
    0.39
    mok
    0.39
    mRNA
    0.37
    Normalization
    0.37
     Mok
    0.36
     Political
    0.36
     Norm
    0.35
     Chemical
    0.35
    宣布
    0.35
     autoimmunity
    0.35
    Act Density 0.000%

    No Known Activations