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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ahmed
    -0.07
     phone
    -0.07
    䎖
    -0.07
    abd
    -0.07
     Morris
    -0.07
     Tv
    -0.07
     Allen
    -0.07
    ᥖ
    -0.07
     Charm
    -0.06
     peeled
    -0.06
    POSITIVE LOGITS
    本次活动
    0.08
    的办法
    0.07
     לפי
    0.07
     pitcher
    0.07
    irect
    0.07
    下巴
    0.07
     similarly
    0.07
    彘
    0.07
    ansas
    0.07
     практически
    0.07
    Act Density 0.057%

    No Known Activations