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

    Neuronpedia

    INDEX
    Explanations

    potato chips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.72
    ë
    0.69
     toddler
    0.60
    ８
    0.59
     child
    0.57
    child
    0.55
    る
    0.55
    schaft
    0.54
     thermodynamic
    0.54
     dossiers
    0.54
    POSITIVE LOGITS
    ुल
    0.64
    _
    0.57
     اللجنة
    0.56
    iciona
    0.55
    ल
    0.52
     किताब
    0.52
    ினி
    0.51
     esiste
    0.51
    म
    0.51
    𝒌
    0.51
    Act Density 0.002%

    No Known Activations