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

    Neuronpedia

    INDEX
    Explanations

    more information or access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ధ్య
    0.45
    ادرة
    0.44
    TARGETTING
    0.44
    ᒡ
    0.43
    रेन्द्र
    0.42
     เหรอ
    0.42
     ""`
    0.42
     září
    0.42
    ंगी
    0.41
    ણી
    0.41
    POSITIVE LOGITS
    weight
    0.51
    Weight
    0.47
    species
    0.46
     forage
    0.46
    const
    0.46
     weight
    0.46
    if
    0.44
    source
    0.43
    match
    0.43
     weights
    0.43
    Act Density 0.005%

    No Known Activations