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

    Neuronpedia

    INDEX
    Explanations

    中文

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Brains
    -0.07
    .choose
    -0.07
    appers
    -0.07
    spi
    -0.06
    addon
    -0.06
     ominous
    -0.06
    .getS
    -0.06
    Й
    -0.06
    анси
    -0.06
     getClient
    -0.06
    POSITIVE LOGITS
    中文
    0.11
     steering
    0.07
    人
    0.06
     dbl
    0.06
     scl
    0.06
     COMMENTS
    0.06
     lắng
    0.06
     --------------------------------------------------------------------------↵
    0.06
     holistic
    0.06
     âm
    0.06
    Act Density 0.005%

    No Known Activations