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

    Neuronpedia

    INDEX
    Explanations

    Technical and informational excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     веществ
    -0.07
    mc
    -0.07
    subtype
    -0.06
    -B
    -0.06
    _PRI
    -0.06
     glorious
    -0.06
     nevid
    -0.06
    +n
    -0.06
    .ship
    -0.06
     ii
    -0.06
    POSITIVE LOGITS
    .
↵
    0.07
     metals
    0.07
    >({↵
    0.07
     Cath
    0.07
     );
↵
↵
    0.06
    Crow
    0.06
    Tam
    0.06
    filtro
    0.06
     dele
    0.06
    .Zero
    0.06
    Act Density 0.090%

    No Known Activations