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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sag
    -0.07
     глаза
    -0.07
    作文
    -0.07
    ుతూ
    -0.07
     айту
    -0.07
    φαν
    -0.07
    Faire
    -0.07
    ocate
    -0.07
    XD
    -0.07
     చెప్పారు
    -0.07
    POSITIVE LOGITS
     hieronder
    0.12
    👇
    0.11
     below
    0.11
    below
    0.10
     아래
    0.10
     abaixo
    0.09
     ниже
    0.09
     abajo
    0.09
     verða
    0.09
     नीचे
    0.08
    Act Density 0.025%

    No Known Activations