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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izi
    -0.07
    .quest
    -0.07
    ーション
    -0.07
    recommend
    -0.07
    ༜
    -0.06
    옯
    -0.06
    国庆
    -0.06
    𬳿
    -0.06
    reta
    -0.06
    _virtual
    -0.06
    POSITIVE LOGITS
    ་
    0.08
    __.
    0.07
    errors
    0.07
    �
    0.07
    โรงงาน
    0.07
    _RAW
    0.07
    spawn
    0.06
    ()}
    0.06
     ע
    0.06
    ::{↵
    0.06
    Act Density 0.001%

    No Known Activations