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

    Neuronpedia

    INDEX
    Explanations

    modification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ститут
    -0.08
    Mah
    -0.07
    .Components
    -0.06
    >');
    -0.06
     Jes
    -0.06
     prominently
    -0.06
    …I
    -0.06
    ANTE
    -0.06
    %-
    -0.06
     VERY
    -0.06
    POSITIVE LOGITS
    anka
    0.08
     carte
    0.07
     Luna
    0.06
    chein
    0.06
     goodwill
    0.06
     ein
    0.06
     api
    0.06
     anyways
    0.06
     basit
    0.06
    コード
    0.06
    Act Density 0.004%

    No Known Activations