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

    Neuronpedia

    INDEX
    Explanations

    letting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     might
    -0.07
    代表
    -0.07
     representing
    -0.07
    许可
    -0.07
     admittedly
    -0.07
     Money
    -0.07
    plays
    -0.07
    媸
    -0.06
     extremists
    -0.06
    뭬
    -0.06
    POSITIVE LOGITS
     parach
    0.07
     рай
    0.07
    自然界
    0.07
    十堰
    0.07
    اص
    0.07
    堰
    0.07
     bron
    0.07
    apeutic
    0.06
    \base
    0.06
     Oral
    0.06
    Act Density 0.065%

    No Known Activations