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

    Neuronpedia

    INDEX
    Explanations

    mathematical equivalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iscipline
    -0.09
    ুষ
    -0.08
    (KERN
    -0.08
    _TCP
    -0.08
     temperament
    -0.07
    _ls
    -0.07
    *)(
    -0.07
     Theodore
    -0.07
     broj
    -0.07
     темпера
    -0.07
    POSITIVE LOGITS
     dianggap
    0.09
     uniqu
    0.08
    Duplicates
    0.08
     uniqueness
    0.08
    との差
    0.08
     indist
    0.08
     θεω
    0.07
     duplicate
    0.07
     flask
    0.07
    違
    0.07
    Act Density 0.015%

    No Known Activations