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

    Neuronpedia

    INDEX
    Explanations

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     digitally
    -0.07
    rün
    -0.07
    /l
    -0.07
    obox
    -0.06
     ]
    -0.06
    ordo
    -0.06
    рож
    -0.06
     Qué
    -0.06
    طن
    -0.06
    Bow
    -0.06
    POSITIVE LOGITS
    пат
    0.06
    赞
    0.06
     tous
    0.06
     homelessness
    0.06
    Ｒ
    0.06
     seperate
    0.06
     keeping
    0.06
     familiarity
    0.06
     хвилин
    0.06
     профессиональ
    0.06
    Act Density 0.041%

    No Known Activations