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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winters
    -0.29
    Triple
    -0.27
    DTV
    -0.27
    _subtype
    -0.26
    subtype
    -0.25
     Triple
    -0.25
     triple
    -0.25
     computers
    -0.25
    gee
    -0.24
    .mozilla
    -0.24
    POSITIVE LOGITS
    å¸Ĥ
    0.30
    rians
    0.27
    åīįåĪĹ
    0.27
    board
    0.26
    rian
    0.26
    زاÙĦ
    0.26
    æ²īæ·Ģ
    0.25
    ina
    0.25
     sticking
    0.25
     Admir
    0.25
    Act Density 0.007%

    No Known Activations