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

    Neuronpedia

    INDEX
    Explanations

    descriptive buzzwords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    決して
    0.37
    organization
    0.36
     şunu
    0.36
    ள்ளதாக
    0.36
     പിന്നീട്
    0.35
    予以
    0.35
    若い
    0.35
     regarding
    0.35
     bersifat
    0.34
    按照
    0.34
    POSITIVE LOGITS
     shenanigans
    0.76
     extravaganza
    0.75
     mayhem
    0.71
     prowess
    0.69
     supremacy
    0.68
     madness
    0.67
     wonderland
    0.66
     galore
    0.64
     vibes
    0.64
     spree
    0.62
    Act Density 0.074%

    No Known Activations