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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⵉ
    -0.08
    ዶ
    -0.06
    _editor
    -0.06
    枕
    -0.06
    _MAP
    -0.06
    ⴽ
    -0.06
    иде
    -0.06
    _HOT
    -0.06
    /home
    -0.06
    _CPP
    -0.06
    POSITIVE LOGITS
    ออนไล
    0.08
    低温
    0.07
    劉
    0.07
     Minh
    0.07
     modelo
    0.07
     BN
    0.07
     Он
    0.07
     haar
    0.07
     crow
    0.07
    浠
    0.07
    Act Density 0.005%

    No Known Activations