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

    Neuronpedia

    INDEX
    Explanations

    eggs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     Probably
    -0.07
    �
    -0.07
     prosperous
    -0.07
     Diseases
    -0.06
    -0.06
     political
    -0.06
     Disease
    -0.06
    タ
    -0.06
     Burning
    -0.06
    POSITIVE LOGITS
    oms
    0.06
    osas
    0.06
    >-
    0.06
    Impl
    0.06
     triang
    0.06
    ...,
    0.06
     scout
    0.06
    ъек
    0.06
     ήταν
    0.06
     注意
    0.06
    Act Density 0.075%

    No Known Activations