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

    Neuronpedia

    INDEX
    Explanations

    free, confidential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lap
    0.47
    lap
    0.45
    Cpu
    0.42
    B
    0.40
    Lap
    0.39
     LAP
    0.38
    Mo
    0.38
     Lap
    0.38
    LAP
    0.37
     tar
    0.37
    POSITIVE LOGITS
     Neel
    0.39
     Her
    0.37
    薪
    0.37
     Adam
    0.36
    ʻ
    0.36
     Anton
    0.36
    Ѡ
    0.36
     Ranj
    0.36
     Бала
    0.35
     Sel
    0.35
    Act Density 0.005%

    No Known Activations