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

    Neuronpedia

    INDEX
    Explanations

    Code/graph representations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     один
    -0.07
    פיר
    -0.06
    .ie
    -0.06
    タン
    -0.06
    bine
    -0.06
    病毒
    -0.06
    .fix
    -0.06
    <!--↵
    -0.06
    借款人
    -0.06
    辛
    -0.06
    POSITIVE LOGITS
     üst
    0.08
    paging
    0.07
    _hostname
    0.07
    SELF
    0.07
     Hamas
    0.07
    uggy
    0.07
     sécur
    0.07
    -black
    0.07
    toBeDefined
    0.07
    SHOT
    0.07
    Act Density 0.051%

    No Known Activations