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

    Neuronpedia

    INDEX
    Explanations

    soaring energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     требу
    0.42
    jsdel
    0.42
     amel
    0.42
    wak
    0.41
     shadowing
    0.40
    깼
    0.40
     indoct
    0.39
    ROG
    0.38
     awakening
    0.38
     metastases
    0.38
    POSITIVE LOGITS
     Spann
    0.44
     লগ
    0.42
     cứ
    0.41
    SizeF
    0.40
     montée
    0.39
     every
    0.39
     आगे
    0.38
    对象的
    0.38
     Handwritten
    0.38
     Aust
    0.38
    Act Density 0.000%

    No Known Activations