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

    Neuronpedia

    INDEX
    Explanations

    improve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nickname
    -0.08
     pyt
    -0.07
    遍
    -0.07
    cms
    -0.07
    Cumhurba
    -0.07
    tokenizer
    -0.07
    ただし
    -0.07
    .gpu
    -0.07
     Orn
    -0.07
    め
    -0.07
    POSITIVE LOGITS
     initiating
    0.07
     incoming
    0.07
     영화
    0.07
    退役
    0.07
     위치
    0.07
     mafia
    0.07
     marital
    0.07
    /Open
    0.07
     העוב
    0.06
     attached
    0.06
    Act Density 0.000%

    No Known Activations