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

    Neuronpedia

    INDEX
    Explanations

    prizes to win

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.71
     creation
    0.55
    ി
    0.54
    ر
    0.52
    ી
    0.51
     C
    0.50
    Ci
    0.50
    ري
    0.49
    ো
    0.49
    た
    0.49
    POSITIVE LOGITS
     ayahuasca
    0.52
     davon
    0.51
    mh
    0.51
    mad
    0.50
    mé
    0.49
     amerikan
    0.49
     retorted
    0.48
    vrdr
    0.47
     passant
    0.47
    leistungen
    0.46
    Act Density 0.003%

    No Known Activations