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

    Neuronpedia

    INDEX
    Explanations

    offset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vacuum
    -0.07
    _lim
    -0.07
     sendMessage
    -0.06
     Vale
    -0.06
    -cache
    -0.06
    ours
    -0.06
    pections
    -0.06
    loyment
    -0.06
    primir
    -0.06
     absolut
    -0.06
    POSITIVE LOGITS
     offset
    0.10
     Ξ
    0.07
     Offset
    0.07
    tuğ
    0.07
    _hat
    0.07
    fx
    0.07
    Odd
    0.07
     offsets
    0.07
     spiritually
    0.07
    FTA
    0.07
    Act Density 0.002%

    No Known Activations