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

    Neuronpedia

    INDEX
    Explanations

    fully transparent, discretion in, saving your, check availability, report suspicious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gardens
    0.43
    DidEnter
    0.42
    적인
    0.40
    CGPoint
    0.40
    годня
    0.40
     stamina
    0.39
     präsent
    0.39
    čan
    0.38
    캠
    0.38
     campfire
    0.38
    POSITIVE LOGITS
    르
    0.51
     allClasses
    0.44
     všetky
    0.44
    冂
    0.43
    數
    0.42
    鍱
    0.42
    ర్గ
    0.40
    ।]
    0.40
     echelon
    0.40
    𝐫
    0.40
    Act Density 0.003%

    No Known Activations