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

    Neuronpedia

    INDEX
    Explanations

    detailed concept breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    removeClass
    0.40
     पढ़ाया
    0.40
     retraining
    0.38
    صيل
    0.37
     warum
    0.37
    Decoding
    0.37
     типи
    0.37
    普遍
    0.35
     symmetric
    0.34
     причина
    0.34
    POSITIVE LOGITS
     sketches
    1.69
     sketch
    1.66
     sketched
    1.62
    Sketch
    1.55
     Sketch
    1.50
    sketch
    1.48
     outline
    1.44
     sketching
    1.44
     esboço
    1.40
     brainstorming
    1.38
    Act Density 0.170%

    No Known Activations