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

    Neuronpedia

    INDEX
    Explanations

    doing actions oneself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pling
    0.40
    ள்
    0.40
    ৩৭
    0.39
    陬
    0.38
    یہ
    0.38
    铍
    0.38
    ksi
    0.38
     този
    0.38
     ഉള്ള
    0.37
    ipv
    0.37
    POSITIVE LOGITS
     basée
    0.42
     gymnast
    0.40
     **
    0.39
     angepasst
    0.39
     empower
    0.38
     basada
    0.38
    มากกว่า
    0.38
    ပေး
    0.38
     journalist
    0.37
     effectués
    0.36
    Act Density 0.002%

    No Known Activations