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

    Neuronpedia

    INDEX
    Explanations

    Variant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Combat
    -0.07
     Rowling
    -0.07
     medidas
    -0.07
    Roman
    -0.07
     issuer
    -0.07
     جامعة
    -0.07
     cores
    -0.06
    \L
    -0.06
    这么
    -0.06
     npc
    -0.06
    POSITIVE LOGITS
    erals
    0.07
     �
    0.07
    ฑ
    0.06
     prot
    0.06
    xygen
    0.06
     grit
    0.06
    GRAPH
    0.06
    etro
    0.06
    aside
    0.06
    AGIC
    0.05
    Act Density 0.001%

    No Known Activations