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

    Neuronpedia

    INDEX
    Explanations

    whole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jealous
    -0.07
    dept
    -0.07
     amis
    -0.06
    mnop
    -0.06
     foe
    -0.06
     suma
    -0.06
    гов
    -0.06
    AK
    -0.06
    (strings
    -0.06
    顯
    -0.06
    POSITIVE LOGITS
    iasco
    0.07
    slot
    0.07
     araştırma
    0.07
     ảnh
    0.06
     Й
    0.06
    ována
    0.06
     ανα
    0.06
    svc
    0.06
    vented
    0.06
     nedenle
    0.06
    Act Density 0.008%

    No Known Activations