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

    Neuronpedia

    INDEX
    Explanations

    to help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toxic
    0.44
    cur
    0.41
     соотно
    0.39
    cil
    0.38
    west
    0.38
     نقص
    0.38
    punctuation
    0.37
    relaxed
    0.37
    neck
    0.37
    compound
    0.36
    POSITIVE LOGITS
    躲
    0.43
     descripcion
    0.42
    ಗೋ
    0.42
     Improvements
    0.39
    🫣
    0.39
     dodging
    0.38
    拃
    0.38
     slaughter
    0.38
    ผู้ชมในสนาม
    0.38
    Improvements
    0.38
    Act Density 0.001%

    No Known Activations