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

    Neuronpedia

    INDEX
    Explanations

    Everest yearly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ts
    0.54
     electrified
    0.49
    ಿದರು
    0.48
     بجلی
    0.47
    rupted
    0.46
    idescent
    0.46
    BleStatus
    0.46
     півні
    0.46
    inio
    0.45
     ی
    0.44
    POSITIVE LOGITS
    ండ
    0.50
     PATCH
    0.47
     Tone
    0.46
     Wednesday
    0.46
     nějak
    0.46
     Activate
    0.45
     CYAN
    0.45
     Programmer
    0.45
     Springs
    0.45
     Array
    0.45
    Act Density 0.000%

    No Known Activations