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

    Neuronpedia

    INDEX
    Explanations

    rule of thumb guideline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ständig
    0.77
    holung
    0.77
     همین
    0.75
     صدای
    0.74
    irstyle
    0.74
     sürü
    0.73
    stellt
    0.73
    este
    0.71
    ┈
    0.71
     বিপুল
    0.71
    POSITIVE LOGITS
     thumb
    1.29
     Thumb
    1.24
     rule
    1.24
    Thumb
    1.15
     правило
    1.13
    Rule
    1.08
     Rule
    1.06
    rule
    1.06
     guideline
    1.02
    thumb
    1.01
    Act Density 0.063%

    No Known Activations