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

    Neuronpedia

    INDEX
    Explanations

    higher fiber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anderem
    0.50
    糗
    0.46
     oth
    0.46
     శరీ
    0.44
    筅
    0.44
     lequel
    0.44
     pire
    0.44
     OTHER
    0.44
     andere
    0.43
     otras
    0.42
    POSITIVE LOGITS
    existence
    0.43
    救
    0.42
    矯
    0.39
    ასი
    0.38
    ന്നു
    0.38
    муще
    0.37
    varying
    0.36
     varying
    0.36
    esthetic
    0.35
    ęcia
    0.35
    Act Density 0.000%

    No Known Activations