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

    Neuronpedia

    INDEX
    Explanations

    Florida

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scheduling
    -0.08
     catalog
    -0.07
     timing
    -0.07
    _tau
    -0.07
     early
    -0.07
     כ
    -0.07
     warranty
    -0.07
    perm
    -0.07
     loro
    -0.07
    .Today
    -0.07
    POSITIVE LOGITS
    _sin
    0.08
     devastation
    0.07
    敗
    0.07
     humiliation
    0.07
    �
    0.07
    的区别
    0.06
    شعوب
    0.06
    ITT
    0.06
     ByteArray
    0.06
     Jerusalem
    0.06
    Act Density 0.001%

    No Known Activations