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

    Neuronpedia

    INDEX
    Explanations

    away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ERE
    0.54
    ASE
    0.47
    ation
    0.45
     at
    0.45
    Creation
    0.45
    nate
    0.45
    :
    0.44
    м
    0.44
     kim
    0.44
    ?
    0.44
    POSITIVE LOGITS
     कक्क
    0.51
    angulo
    0.51
    ᄈ
    0.50
    πος
    0.50
     hossz
    0.49
    大脑
    0.48
    휼
    0.48
    Ƹ
    0.48
     оттен
    0.48
    getFocusAreas
    0.47
    Act Density 0.000%

    No Known Activations