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

    Neuronpedia

    INDEX
    Explanations

    hypothetical situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Romantic
    -0.07
    怩
    -0.07
    	restore
    -0.07
    (strlen
    -0.07
     comme
    -0.06
    ому
    -0.06
    legalArgumentException
    -0.06
    指挥部
    -0.06
    ką
    -0.06
    Ὡ
    -0.06
    POSITIVE LOGITS
     Classe
    0.08
     alternatives
    0.08
    -shaped
    0.07
     Gh
    0.07
    装配
    0.07
     chloride
    0.07
    /plugins
    0.07
     tensors
    0.07
    ✴
    0.07
     mars
    0.07
    Act Density 0.050%

    No Known Activations