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

    Neuronpedia

    INDEX
    Explanations

    Add references to API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     song
    0.42
    ജീവ
    0.40
     जिन्होंने
    0.39
     아름
    0.38
     beautifully
    0.38
     gorgeous
    0.37
     immensely
    0.37
     গানের
    0.36
     Pendleton
    0.36
    esta
    0.36
    POSITIVE LOGITS
    theit
    0.44
     എന്നു
    0.44
    vao
    0.43
    шлай
    0.43
    ような
    0.42
     αλλά
    0.41
    FlightID
    0.41
    ⏭
    0.41
    backing
    0.41
    აცი
    0.40
    Act Density 0.000%

    No Known Activations