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

    Neuronpedia

    INDEX
    Explanations

    paragraph tags `</p>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стіше
    0.44
    ní
    0.44
    ημ
    0.43
    そろ
    0.43
     harrow
    0.42
    ьогодні
    0.42
    tt
    0.41
    ﹍
    0.41
    ochet
    0.41
    leurs
    0.41
    POSITIVE LOGITS
     SEQUENCE
    0.39
     directional
    0.38
     PA
    0.38
     reflection
    0.38
     reaction
    0.38
     FT
    0.37
     stream
    0.37
     massage
    0.37
     surface
    0.37
    টিক
    0.36
    Act Density 0.001%

    No Known Activations