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

    Neuronpedia

    INDEX
    Explanations

    agreement or Portugal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Read
    0.63
     read
    0.50
    read
    0.49
    Read
    0.43
    ︾
    0.41
    薔
    0.40
    玫瑰
    0.39
    getMaster
    0.39
    敀
    0.39
    MAPb
    0.38
    POSITIVE LOGITS
    reading
    0.44
     reading
    0.40
    Reading
    0.38
     hardest
    0.38
     uma
    0.37
     하는
    0.37
     हवे
    0.37
     equipes
    0.36
    inti
    0.36
     nodules
    0.36
    Act Density 0.001%

    No Known Activations