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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scal
    -0.08
     scaff
    -0.08
    蜍
    -0.07
    ское
    -0.07
     incident
    -0.07
     reveal
    -0.07
    His
    -0.07
    쉐
    -0.06
     gauge
    -0.06
    iasi
    -0.06
    POSITIVE LOGITS
     detections
    0.07
    ᴥ
    0.07
    GY
    0.07
    //----------------------------------------------------------------------------↵
    0.07
    enez
    0.07
    ᒌ
    0.06
    .password
    0.06
    נגד
    0.06
     Dedicated
    0.06
     dạy
    0.06
    Act Density 0.008%

    No Known Activations