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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    菟
    -0.07
    thern
    -0.06
     bathing
    -0.06
     Cand
    -0.06
    חלת
    -0.06
     craftsm
    -0.06
    书中
    -0.06
    铘
    -0.06
     distributed
    -0.06
    Del
    -0.06
    POSITIVE LOGITS
     infancy
    0.08
    责任制
    0.08
    Terminal
    0.07
     sábado
    0.07
     initiative
    0.07
     Frankfurt
    0.07
    MEMORY
    0.07
    Received
    0.07
    (scale
    0.07
    AllowAnonymous
    0.07
    Act Density 0.001%

    No Known Activations