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

    Neuronpedia

    INDEX
    Explanations

    foreign and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \},\{
    0.49
    ็ว
    0.46
     amely
    0.45
    Evaluate
    0.44
    Пере
    0.42
    Govern
    0.42
    ш
    0.42
    广
    0.42
    Broad
    0.41
     Loads
    0.41
    POSITIVE LOGITS
     BCCI
    0.47
     INSEE
    0.42
    点で
    0.40
    democratic
    0.40
     bukan
    0.40
     RetValue
    0.39
    ંત્રી
    0.39
     OOP
    0.39
     politico
    0.39
     FRA
    0.38
    Act Density 0.002%

    No Known Activations