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

    Neuronpedia

    INDEX
    Explanations

    hot or warm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ꭼ
    -0.08
    義務
    -0.07
    ды
    -0.07
     Relations
    -0.07
     Fs
    -0.07
    徒步
    -0.07
     pelvic
    -0.07
    废弃
    -0.07
     Highest
    -0.07
     Msg
    -0.07
    POSITIVE LOGITS
    ammu
    0.07
    ––
    0.06
    Assembly
    0.06
    뀜
    0.06
    Marco
    0.06
    �
    0.06
     /*↵
    0.06
    邻
    0.06
    ☷
    0.06
    Clipboard
    0.06
    Act Density 0.013%

    No Known Activations