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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pci
    -0.07
    ym
    -0.06
     Typeface
    -0.06
     потому
    -0.06
    alli
    -0.06
    >L
    -0.06
    ween
    -0.06
    swer
    -0.06
     акку
    -0.06
    uyu
    -0.06
    POSITIVE LOGITS
     blending
    0.07
     سرعت
    0.07
    (off
    0.06
     Relay
    0.06
    şam
    0.06
     각각
    0.06
     Vec
    0.06
    滑
    0.06
    ış
    0.06
    Strange
    0.06
    Act Density 0.029%

    No Known Activations