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

    Neuronpedia

    INDEX
    Explanations

    technical concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     REM
    -0.07
    ันย
    -0.07
     they
    -0.07
     तक
    -0.07
    odcast
    -0.06
     artık
    -0.06
    _MIX
    -0.06
    maps
    -0.06
    ί
    -0.06
     管
    -0.06
    POSITIVE LOGITS
    actable
    0.06
     pending
    0.06
     пласти
    0.06
     چاپ
    0.06
    mayacak
    0.06
    _ss
    0.06
     �
    0.06
    nesday
    0.06
    (tensor
    0.06
     Charlottesville
    0.06
    Act Density 0.396%

    No Known Activations