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

    Neuronpedia

    INDEX
    Explanations

    php code blocks `<?`, `<%`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    étr
    0.40
    ەی
    0.38
    ကြီး
    0.36
    fuels
    0.35
     میچ
    0.34
     राहि
    0.34
    Derived
    0.33
     হীর
    0.33
    arreg
    0.33
    பெரு
    0.33
    POSITIVE LOGITS
     //}
    0.44
     include
    0.40
     Sidney
    0.39
     Barra
    0.38
    0.37
     //@
    0.37
    ర్ప
    0.36
     Supervisory
    0.36
     Oba
    0.36
     Sid
    0.36
    Act Density 0.007%

    No Known Activations