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

    Neuronpedia

    INDEX
    Explanations

    echoes of stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !(
    0.42
    Wow
    0.42
    !<
    0.41
    рог
    0.41
    !">
    0.41
    !
    0.40
    everything
    0.40
    ತ್ವ
    0.40
    ለም
    0.39
     gimana
    0.39
    POSITIVE LOGITS
     ऑफ
    0.51
     einer
    0.48
     ఆఫ్
    0.48
     of
    0.48
     ενός
    0.48
    នៃការ
    0.46
     của
    0.45
     ഓഫ്
    0.45
     फ्रॉम
    0.45
     unbound
    0.45
    Act Density 0.021%

    No Known Activations