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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unless
    -0.09
     વિડ
    -0.08
     वीडियो
    -0.08
     frame
    -0.08
     వీడియో
    -0.07
    Frame
    -0.07
    .inter
    -0.07
     ઑ
    -0.07
    Unless
    -0.07
     worldwide
    -0.07
    POSITIVE LOGITS
     allá
    0.11
    ‌تر
    0.10
     जाकर
    0.09
    ward
    0.09
     қарай
    0.09
     cứu
    0.09
     보면
    0.08
    -reaching
    0.08
    ались
    0.08
    оват
    0.08
    Act Density 0.034%

    No Known Activations