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
     distinguished
    -0.08
     transplantation
    -0.08
    fact
    -0.08
     �
    -0.08
     easing
    -0.08
     transplant
    -0.08
     lettre
    -0.07
     तहत
    -0.07
    礼包
    -0.07
     fact
    -0.07
    POSITIVE LOGITS
     Occasionally
    0.10
     Reliability
    0.09
     occasionally
    0.09
     interruptions
    0.09
     робот
    0.08
     Due
    0.08
     الأحيان
    0.08
    可靠
    0.08
     പുറത്ത
    0.08
     occasional
    0.08
    Act Density 0.002%

    No Known Activations