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

    Neuronpedia

    INDEX
    Explanations

    Code and programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     내려
    -0.07
    ました
    -0.06
    �
    -0.06
    ような
    -0.06
    justify
    -0.06
    菜
    -0.06
    oksen
    -0.06
     μα
    -0.06
     Tears
    -0.06
     recebe
    -0.06
    POSITIVE LOGITS
     JOHN
    0.07
     Reviews
    0.07
     grouped
    0.07
    John
    0.07
     semble
    0.07
     communion
    0.07
     John
    0.06
     relative
    0.06
    unsch
    0.06
     Forums
    0.06
    Act Density 0.029%

    No Known Activations