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

    Neuronpedia

    INDEX
    Explanations

    January birthstone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     introductions
    0.91
    bursements
    0.80
     introduces
    0.76
     specifications
    0.75
     stocking
    0.74
     housings
    0.74
     instructs
    0.74
     crowning
    0.73
     wrestle
    0.73
    𝄞
    0.72
    POSITIVE LOGITS
    ip
    0.94
    i
    0.89
     Samar
    0.84
    ো
    0.79
    al
    0.77
    u
    0.77
    Ks
    0.76
    ка
    0.75
     Кы
    0.75
    ีน
    0.75
    Act Density 0.000%

    No Known Activations