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

    Neuronpedia

    INDEX
    Explanations

    unlock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ollapsed
    -0.07
     oh
    -0.07
    �
    -0.07
    bservice
    -0.07
     Değer
    -0.06
     peuvent
    -0.06
     mantra
    -0.06
    保護
    -0.06
     recall
    -0.06
    πτυ
    -0.06
    POSITIVE LOGITS
     Romans
    0.06
     Afghan
    0.06
    reve
    0.06
     bitch
    0.06
    国家
    0.06
    IFICATE
    0.06
     thức
    0.06
     inde
    0.06
    ]){↵
    0.06
     Farmers
    0.06
    Act Density 0.006%

    No Known Activations