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

    Neuronpedia

    INDEX
    Explanations

    attempt to, devices:, intended to, mix with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etc
    0.47
    event
    0.44
    pp
    0.43
     Political
    0.42
    એ
    0.42
     Downtown
    0.41
    rms
    0.40
    সরকারী
    0.40
    上記の
    0.39
    in
    0.39
    POSITIVE LOGITS
    变换
    0.58
    েশ্বর
    0.58
    GraphicsUnit
    0.48
    ър
    0.47
     transformations
    0.45
    Khe
    0.45
     określ
    0.44
     gafas
    0.44
    یسر
    0.43
     oncoming
    0.43
    Act Density 0.005%

    No Known Activations