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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shares
    -0.07
    _CS
    -0.06
     OS
    -0.06
     έναν
    -0.06
    Num
    -0.06
     된다
    -0.06
    ynam
    -0.06
    gm
    -0.06
     Distributed
    -0.05
     галуз
    -0.05
    POSITIVE LOGITS
    lomou
    0.07
    IALOG
    0.06
    створ
    0.06
    aise
    0.06
    etadata
    0.06
    ومان
    0.06
    ै↵
    0.06
     loginUser
    0.06
    ounter
    0.06
     cong
    0.06
    Act Density 0.035%

    No Known Activations