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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consists
    -0.07
    060
    -0.07
     attachments
    -0.06
    OUCH
    -0.06
    149
    -0.06
    loom
    -0.06
     Xiaomi
    -0.06
    (trans
    -0.06
    rops
    -0.06
    813
    -0.06
    POSITIVE LOGITS
    uple
    0.06
    .an
    0.06
     IG
    0.06
    इसक
    0.06
     HF
    0.06
     sci
    0.06
    Det
    0.06
    dration
    0.06
    ‌‌
    0.06
    AN
    0.05
    Act Density 0.134%

    No Known Activations