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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selfies
    -0.07
    /end
    -0.07
    ่าอ
    -0.06
    dikleri
    -0.06
     recreational
    -0.06
     sıcak
    -0.06
    -0.06
    -0.06
    <x
    -0.06
    rogen
    -0.06
    POSITIVE LOGITS
     هزینه
    0.07
     firepower
    0.07
     Karen
    0.06
    csi
    0.06
     Alic
    0.06
     exig
    0.06
     �
    0.06
     however
    0.06
    圣
    0.06
    .concatenate
    0.06
    Act Density 0.014%

    No Known Activations