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

    Neuronpedia

    INDEX
    Explanations

    перед

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _numpy
    -0.07
    .zip
    -0.07
     bath
    -0.06
    嵝
    -0.06
    smart
    -0.06
     logged
    -0.06
    氇
    -0.06
    -month
    -0.06
     nip
    -0.06
    _venta
    -0.06
    POSITIVE LOGITS
     Transactions
    0.08
     traps
    0.07
     blasted
    0.07
    ニュース
    0.07
     +/-
    0.07
    👬
    0.07
     massacre
    0.06
     setSize
    0.06
     Bale
    0.06
     tenemos
    0.06
    Act Density 0.006%

    No Known Activations