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

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    acion
    -0.07
    -network
    -0.07
     жизни
    -0.07
    изма
    -0.07
    ande
    -0.07
    .GetCurrentMethod
    -0.07
     RULE
    -0.06
    関わ
    -0.06
    握手
    -0.06
     Particle
    -0.06
    POSITIVE LOGITS
    (Unknown
    0.07
     החי
    0.07
     mary
    0.06
     specially
    0.06
    商店
    0.06
     Cush
    0.06
     exert
    0.06
    勚
    0.06
    垩
    0.06
    云南省
    0.06
    Act Density 0.230%

    No Known Activations