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

    Neuronpedia

    INDEX
    Explanations

    adjacent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不知
    -0.07
    🏝
    -0.07
     develop
    -0.07
    pass
    -0.07
     większe
    -0.07
     wx
    -0.07
    ꙋ
    -0.07
     step
    -0.07
    採取
    -0.06
     Once
    -0.06
    POSITIVE LOGITS
     politely
    0.08
     openssl
    0.08
     depressing
    0.08
     usando
    0.08
    _BITS
    0.07
    😼
    0.07
     влия
    0.07
    (priority
    0.07
    铌
    0.07
     Brigham
    0.07
    Act Density 0.013%

    No Known Activations