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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     displayed
    -0.07
    ột
    -0.07
    腐蚀
    -0.06
    .Screen
    -0.06
    כול
    -0.06
    orsi
    -0.06
    ube
    -0.06
    -ce
    -0.06
    _Add
    -0.06
     crap
    -0.06
    POSITIVE LOGITS
    (accounts
    0.07
    .layer
    0.07
    _age
    0.07
     "../../
    0.07
    _INTERFACE
    0.07
    _REFERER
    0.07
     LocalDateTime
    0.07
    \Model
    0.07
    נן
    0.07
    建筑工程
    0.07
    Act Density 0.009%

    No Known Activations