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

    Neuronpedia

    INDEX
    Explanations

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лим
    -0.07
    cete
    -0.06
    SZ
    -0.06
     chấm
    -0.06
    แพ
    -0.06
     dikke
    -0.06
     hust
    -0.06
    nut
    -0.06
    rompt
    -0.06
    、マ
    -0.06
    POSITIVE LOGITS
    pairs
    0.07
     Druid
    0.07
    Paul
    0.06
    patial
    0.06
     UserModel
    0.06
     Krishna
    0.06
    _Node
    0.06
     recep
    0.06
     Points
    0.06
     possessing
    0.06
    Act Density 0.016%

    No Known Activations