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

    Neuronpedia

    INDEX
    Explanations

    Descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uclear
    -0.07
    useum
    -0.07
    _LR
    -0.07
     friendship
    -0.06
    :@{
    -0.06
     genau
    -0.06
    茂
    -0.06
    �
    -0.06
    êu
    -0.06
    ôn
    -0.06
    POSITIVE LOGITS
     CHRIST
    0.06
     现
    0.06
     traits
    0.06
     excessive
    0.06
    ath
    0.06
     OT
    0.06
     Graz
    0.06
    intr
    0.06
     further
    0.06
     bead
    0.06
    Act Density 0.055%

    No Known Activations