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

    Neuronpedia

    INDEX
    Explanations

    won

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _faces
    -0.06
    ASTE
    -0.06
     burgers
    -0.06
    ип
    -0.06
     Metrics
    -0.06
    暖
    -0.06
    _SEQUENCE
    -0.06
     Housing
    -0.06
    منی
    -0.06
     Calls
    -0.06
    POSITIVE LOGITS
    .usuario
    0.07
    .
↵↵
    0.07
    (txt
    0.06
    .FileName
    0.06
     Scarlett
    0.06
     Christopher
    0.06
    }\.[
    0.06
     української
    0.06
     إد
    0.06
     Tre
    0.06
    Act Density 0.031%

    No Known Activations