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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    堞
    -0.07
    $("#
    -0.07
    流转
    -0.07
    疠
    -0.07
    风水
    -0.07
    خارج
    -0.07
    颤抖
    -0.07
    ppe
    -0.07
     latina
    -0.06
    缥
    -0.06
    POSITIVE LOGITS
    Positions
    0.07
     Clifford
    0.07
    ayo
    0.07
     ''),↵
    0.07
    רוג
    0.07
    特别
    0.07
    ].↵
    0.06
     rebounds
    0.06
     refers
    0.06
    之間
    0.06
    Act Density 0.032%

    No Known Activations