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

    Neuronpedia

    INDEX
    Explanations

    code command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ).↵↵↵↵
    -0.07
     数据
    -0.06
     ス
    -0.06
     досить
    -0.06
     シ
    -0.06
    (nullptr
    -0.06
     з
    -0.06
     zač
    -0.06
     друз
    -0.06
    identifier
    -0.06
    POSITIVE LOGITS
     wolves
    0.07
    Recogn
    0.06
     sentient
    0.06
     Alexis
    0.06
     scalability
    0.06
     Sponsor
    0.06
    Added
    0.06
     quicker
    0.06
     glitch
    0.06
    oeff
    0.06
    Act Density 0.032%

    No Known Activations