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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Recommended
    -0.07
     Division
    -0.07
    因地制
    -0.07
     Р
    -0.07
    ဏ
    -0.07
    �
    -0.07
    arness
    -0.07
    .ms
    -0.07
     carcinoma
    -0.07
     חיים
    -0.06
    POSITIVE LOGITS
     SERIAL
    0.07
     stud
    0.07
    啉
    0.07
    ILES
    0.07
    /log
    0.07
    ADING
    0.07
    Soap
    0.07
     chip
    0.07
    ORED
    0.07
    GUI
    0.07
    Act Density 0.044%

    No Known Activations