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

    Neuronpedia

    INDEX
    Explanations

    molecule followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.54
    照片
    0.52
    listView
    0.50
    se
    0.47
     अ
    0.46
    y
    0.46
    ignment
    0.46
    折
    0.46
     सात
    0.45
    lg
    0.44
    POSITIVE LOGITS
     supporting
    0.53
     Reggie
    0.52
     mussels
    0.50
     vampires
    0.49
     mercenaries
    0.49
     cafes
    0.49
     swivel
    0.49
     smoother
    0.48
    ۰
    0.48
     Donnie
    0.48
    Act Density 0.000%

    No Known Activations