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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     官
    -0.07
     Pearson
    -0.06
     �
    -0.06
     nutritious
    -0.06
    chts
    -0.06
     multip
    -0.06
     Cas
    -0.06
     pick
    -0.06
     đông
    -0.06
     zosta
    -0.06
    POSITIVE LOGITS
     sprintf
    0.07
    енні
    0.07
    ¯¯
    0.07
     bew
    0.06
    دهای
    0.06
    ает
    0.06
     أخرى
    0.06
    ichern
    0.06
    ラック
    0.06
    吨
    0.06
    Act Density 0.003%

    No Known Activations