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

    Neuronpedia

    INDEX
    Explanations

    instructions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valves
    0.43
     railings
    0.43
     valve
    0.40
     noises
    0.39
     apocalyptic
    0.39
     authority
    0.39
     Raymond
    0.38
     foggy
    0.38
     soldered
    0.38
    gag
    0.38
    POSITIVE LOGITS
    ابد
    0.41
     بالاتر
    0.39
     semanal
    0.39
    ubmit
    0.39
    MPT
    0.39
    紶
    0.39
    㫻
    0.38
     diplomat
    0.38
    筅
    0.38
    พร
    0.38
    Act Density 0.003%

    No Known Activations