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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pool
    -0.29
    __.__
    -0.29
    åĪĪ
    -0.29
    éĽĨåĽ¢èĤ¡ä»½
    -0.28
     threesome
    -0.28
    drivers
    -0.27
     regist
    -0.26
    &m
    -0.26
    emm
    -0.25
     pool
    -0.25
    POSITIVE LOGITS
    æºIJ
    0.27
    orarily
    0.26
    çIJĨ
    0.26
     morale
    0.26
    oris
    0.25
    UBLIC
    0.24
    theory
    0.24
    oration
    0.24
    åĬ¿
    0.24
    bsp
    0.23
    Act Density 1.585%

    No Known Activations