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

    Neuronpedia

    INDEX
    Explanations

    common words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transgress
    0.34
     pursuit
    0.33
     latter
    0.31
     aggression
    0.31
     reconnaissance
    0.31
     perfusion
    0.31
     overarching
    0.31
     concentration
    0.31
     moving
    0.30
     pursues
    0.30
    POSITIVE LOGITS
     सिंपली
    0.33
    Good
    0.32
    句话
    0.32
    And
    0.32
     умолчанию
    0.31
     标准
    0.31
    一般来说
    0.31
    ໊
    0.31
    Ą
    0.31
     informazioni
    0.30
    Act Density 0.906%

    No Known Activations