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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ITIVE
    -0.07
    ONSE
    -0.07
    .High
    -0.07
    /hash
    -0.07
     Kil
    -0.07
    Pros
    -0.06
    𝒍
    -0.06
    tá
    -0.06
     rotates
    -0.06
     RTAL
    -0.06
    POSITIVE LOGITS
     угол
    0.07
    神器
    0.06
    egree
    0.06
    inbox
    0.06
    萝卜
    0.06
    _Server
    0.06
     rogue
    0.06
    rz
    0.06
    rant
    0.06
    传媒
    0.06
    Act Density 0.021%

    No Known Activations