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

    Neuronpedia

    INDEX
    Explanations

    halfway out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ôn
    0.45
    Electro
    0.44
     Electro
    0.40
     consci
    0.40
     fréqu
    0.39
     electro
    0.38
    लेक्ट
    0.37
    یات
    0.37
    electro
    0.37
    Ola
    0.37
    POSITIVE LOGITS
     turning
    0.51
     turned
    0.50
     Turning
    0.42
    turning
    0.40
     Villain
    0.39
     Turned
    0.39
     সমর্থন
    0.38
    のエ
    0.37
     villain
    0.37
    တွေကို
    0.37
    Act Density 0.000%

    No Known Activations