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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     potatoes
    -0.07
     compromise
    -0.07
     Fell
    -0.06
    .Stat
    -0.06
    상을
    -0.06
     durumunda
    -0.06
     Procedure
    -0.06
    ẫ
    -0.06
    �
    -0.06
     Norwich
    -0.06
    POSITIVE LOGITS
     asm
    0.07
    UGC
    0.07
     engulf
    0.06
    proto
    0.06
    ROUGH
    0.06
    _coordinate
    0.06
    izyon
    0.06
    Units
    0.06
     backlog
    0.06
     акту
    0.06
    Act Density 0.005%

    No Known Activations