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

    Neuronpedia

    INDEX
    Explanations

    monitoring hearth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॉप
    0.37
     motors
    0.34
    這個
    0.34
     premium
    0.34
     adapter
    0.34
    ្នុង
    0.34
     generator
    0.33
     lasers
    0.33
     uploads
    0.33
    EXP
    0.33
    POSITIVE LOGITS
    㳡
    0.36
    alarını
    0.36
    addContainerGap
    0.35
    Como
    0.34
    Colonel
    0.34
    indazole
    0.34
    Bec
    0.34
    🏤
    0.34
     Beckham
    0.34
    Domic
    0.33
    Act Density 0.000%

    No Known Activations