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

    Neuronpedia

    INDEX
    Explanations

    IoT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     civil
    -0.07
     Rock
    -0.07
     HEAD
    -0.07
     commits
    -0.07
    .saved
    -0.07
     gaussian
    -0.06
     spend
    -0.06
    NEY
    -0.06
     workstation
    -0.06
     analysed
    -0.06
    POSITIVE LOGITS
     IoT
    0.14
    фика
    0.06
    Jos
    0.06
    .bool
    0.06
     tq
    0.06
    lol
    0.06
    unlock
    0.06
    مج
    0.06
    """.
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations