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

    Neuronpedia

    INDEX
    Explanations

    maximum length or a stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isotopes
    1.05
     испол
    1.04
    Persons
    1.03
    emony
    1.00
     delectable
    0.95
     klass
    0.92
     gladly
    0.89
     Изда
    0.89
     forearm
    0.88
    餚
    0.88
    POSITIVE LOGITS
    обходимо
    1.09
     arp
    1.05
    "।
    1.03
    iol
    1.02
    mul
    1.02
     Какие
    0.98
    sine
    0.97
     Aucun
    0.96
    ल
    0.95
    iq
    0.95
    Act Density 0.001%

    No Known Activations