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

    Neuronpedia

    INDEX
    Explanations

    explore further or elaborate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clairement
    0.90
     claramente
    0.85
    を使用
    0.83
     çöze
    0.79
    が存在
    0.78
     explique
    0.78
     instructions
    0.77
    instructions
    0.77
     説明
    0.76
     solves
    0.75
    POSITIVE LOGITS
     delve
    1.52
     digging
    1.48
     delving
    1.45
     dig
    1.43
     explore
    1.33
     Further
    1.30
    Further
    1.30
     exploring
    1.28
     further
    1.27
     dive
    1.27
    Act Density 1.085%

    No Known Activations