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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conformity
    -0.08
    밴
    -0.07
    EV
    -0.07
    -owner
    -0.07
    setSize
    -0.07
    ufreq
    -0.07
    鼠标
    -0.07
     Downloads
    -0.07
     roadway
    -0.07
    윔
    -0.07
    POSITIVE LOGITS
    (string
    0.07
    ose
    0.07
    bd
    0.07
    悔
    0.07
     mặc
    0.06
     İs
    0.06
    恋
    0.06
    _picker
    0.06
    _log
    0.06
     avoir
    0.06
    Act Density 0.102%

    No Known Activations