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

    Neuronpedia

    INDEX
    Explanations

    requests/instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -elected
    -0.07
     confront
    -0.07
    cmpeq
    -0.07
     Sydney
    -0.07
    澥
    -0.06
     recruited
    -0.06
    黥
    -0.06
    ฦ
    -0.06
    ideshow
    -0.06
    vron
    -0.06
    POSITIVE LOGITS
    план
    0.07
    评级
    0.07
     �
    0.07
    库
    0.07
    係
    0.07
    Caps
    0.07
     columns
    0.06
    ¹
    0.06
    restaurants
    0.06
     stakeholders
    0.06
    Act Density 0.040%

    No Known Activations