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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prem
    -0.07
    ptom
    -0.07
    anmar
    -0.06
    .branch
    -0.06
    .med
    -0.06
    _recommend
    -0.06
     Spar
    -0.06
    onald
    -0.06
     rage
    -0.06
     Sơn
    -0.06
    POSITIVE LOGITS
     허
    0.07
     Finally
    0.06
    +
    0.06
    ποιη
    0.06
    Here
    0.06
    .SuppressLint
    0.06
    。↵↵↵↵
    0.06
    ATRIX
    0.06
     látky
    0.06
     století
    0.06
    Act Density 0.002%

    No Known Activations