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

    Neuronpedia

    INDEX
    Explanations

    Unstructured text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KER
    -0.07
    ,’
    -0.07
    宪
    -0.07
    ビ
    -0.06
    �
    -0.06
    ichten
    -0.06
    ɝ
    -0.06
    _cmds
    -0.06
    ymmetric
    -0.06
    Hex
    -0.06
    POSITIVE LOGITS
     division
    0.07
     statues
    0.06
     sorte
    0.06
    iola
    0.06
     slate
    0.06
    >";↵
    0.06
    劣
    0.06
     IllegalArgumentException
    0.06
    เสา
    0.06
     showing
    0.06
    Act Density 0.096%

    No Known Activations