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

    Neuronpedia

    INDEX
    Explanations

    Conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Firewall
    -0.07
    ्तर
    -0.06
    状
    -0.06
    ρχ
    -0.06
    目录
    -0.06
    htdocs
    -0.06
     KK
    -0.06
    icits
    -0.06
    좌
    -0.06
    essaging
    -0.06
    POSITIVE LOGITS
     розвит
    0.07
     paren
    0.07
     hudeb
    0.07
     lifting
    0.06
     ENC
    0.06
    items
    0.06
    ●
    0.06
     jenter
    0.06
     shim
    0.06
    ?>"↵
    0.06
    Act Density 0.221%

    No Known Activations