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

    Neuronpedia

    INDEX
    Explanations

    file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    赦
    0.55
    脏
    0.49
     scarc
    0.48
    菌
    0.48
     veto
    0.47
    Shower
    0.46
     disastrous
    0.45
     showers
    0.44
    的第一
    0.44
     подро
    0.44
    POSITIVE LOGITS
    edad
    0.54
    uración
    0.52
     pute
    0.49
     tabla
    0.48
    ↵
    0.46
     Copenhagen
    0.45
     elektrik
    0.45
     Callum
    0.45
    قامة
    0.44
     Esses
    0.44
    Act Density 0.000%

    No Known Activations