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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nav
    -0.07
     jsonObject
    -0.07
     triggers
    -0.06
     tones
    -0.06
    čila
    -0.06
     cid
    -0.06
     tímto
    -0.06
     เขต
    -0.06
     sovereign
    -0.06
     اث
    -0.06
    POSITIVE LOGITS
    打
    0.08
    compression
    0.07
    _grp
    0.07
    ‌ترین
    0.07
    Trying
    0.06
    iště
    0.06
    partner
    0.06
     средств
    0.06
    至少
    0.06
    難
    0.06
    Act Density 0.000%

    No Known Activations