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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    斯
    -0.06
    つ
    -0.06
     honeymoon
    -0.06
     своих
    -0.06
    шел
    -0.06
     Licensed
    -0.06
     �
    -0.06
    Longitude
    -0.06
    _Not
    -0.06
    .exclude
    -0.06
    POSITIVE LOGITS
     journalist
    0.07
     strtok
    0.07
     فصل
    0.07
     give
    0.07
    .At
    0.07
    ;↵
    0.07
    774
    0.06
    370
    0.06
     out
    0.06
    Western
    0.06
    Act Density 0.043%

    No Known Activations