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

    Neuronpedia

    INDEX
    Explanations

    different viewpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Perimeter
    0.39
     perimeter
    0.37
    এখানে
    0.36
     დ
    0.35
    XM
    0.35
    perimeter
    0.35
     rebus
    0.35
    値
    0.35
     cho
    0.34
     প্রথমে
    0.34
    POSITIVE LOGITS
    ሱስ
    0.39
     জাপান
    0.38
    ilai
    0.38
    romino
    0.37
    iazioni
    0.36
    raines
    0.36
     Especially
    0.36
    raisal
    0.35
    Sole
    0.35
    崦
    0.35
    Act Density 0.001%

    No Known Activations