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

    Neuronpedia

    INDEX
    Explanations

    scientific names of species

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snub
    0.44
    檛
    0.43
    jén
    0.41
    遠慮
    0.39
    介護
    0.39
    ጠት
    0.39
     puluh
    0.38
    는
    0.38
    中心
    0.38
    들어
    0.37
    POSITIVE LOGITS
    ensis
    0.49
     var
    0.42
    os
    0.41
     E
    0.40
    rods
    0.39
     alumni
    0.39
     hasattr
    0.38
    aS
    0.38
    do
    0.37
     Einstein
    0.37
    Act Density 0.007%

    No Known Activations