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

    Neuronpedia

    INDEX
    Explanations

    sample

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дит
    -0.07
     Recap
    -0.07
     بده
    -0.07
    StateManager
    -0.07
     hosts
    -0.06
    on
    -0.06
     therapy
    -0.06
    ิกายน
    -0.06
     liability
    -0.06
    special
    -0.06
    POSITIVE LOGITS
    odox
    0.06
     dobu
    0.06
     messing
    0.06
    υτό
    0.06
    510
    0.06
     �
    0.06
    Reflect
    0.06
    rabbit
    0.06
    物理
    0.06
    킹
    0.06
    Act Density 0.031%

    No Known Activations