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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ξε
    -0.07
    pling
    -0.07
     Resolve
    -0.07
     Exclude
    -0.07
     Runner
    -0.07
    [w
    -0.06
    规
    -0.06
    [a
    -0.06
     XPAR
    -0.06
     будут
    -0.06
    POSITIVE LOGITS
    관
    0.07
    的事情
    0.07
    _auth
    0.06
    -pop
    0.06
     사랑
    0.06
    andle
    0.06
     \''
    0.06
    、それ
    0.06
    :Any
    0.06
    orno
    0.06
    Act Density 0.384%

    No Known Activations