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

    Neuronpedia

    INDEX
    Explanations

    numbers and ranges often followed by qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thisobject
    0.39
     hatte
    0.32
     InMemory
    0.32
    🈚
    0.32
    ropoda
    0.32
    ゴルフクラブ
    0.32
    xyplot
    0.32
     aswell
    0.32
     познакоми
    0.32
     TMN
    0.32
    POSITIVE LOGITS
    depending
    0.57
     depending
    0.57
     dependiendo
    0.48
     Depending
    0.48
     tergantung
    0.44
     higher
    0.44
     varía
    0.44
    higher
    0.42
     Depends
    0.42
    excluding
    0.42
    Act Density 0.318%

    No Known Activations