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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    邈
    -0.08
    螟
    -0.07
    芴
    -0.07
     formerly
    -0.07
     OD
    -0.07
    essages
    -0.07
    JoinColumn
    -0.07
    ခ
    -0.07
    ㄨ
    -0.07
     heroin
    -0.06
    POSITIVE LOGITS
     �
    0.07
    去买
    0.07
    fr
    0.07
    stm
    0.07
     fundraiser
    0.07
     circles
    0.07
    bah
    0.07
     �
    0.06
    牺牲
    0.06
    che
    0.06
    Act Density 0.002%

    No Known Activations