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

    Neuronpedia

    INDEX
    Explanations

    splitting data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stof
    0.41
     gehad
    0.40
    的公司
    0.40
    悗
    0.39
    漱
    0.38
     company
    0.36
    lick
    0.36
     sciatic
    0.36
    的山
    0.36
    ，$
    0.36
    POSITIVE LOGITS
    Separ
    0.45
    Join
    0.44
     Join
    0.42
    Ext
    0.40
     Separ
    0.40
    Ad
    0.40
    Release
    0.38
    Tempor
    0.38
     Independ
    0.38
     Independence
    0.38
    Act Density 0.000%

    No Known Activations