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

    Neuronpedia

    INDEX
    Explanations

    Save then specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creeps
    0.35
     বণ্টন
    0.34
     addirittura
    0.33
     জীবের
    0.32
     basados
    0.32
    creep
    0.31
    ？」
    0.31
     arrhythmias
    0.30
     infrastrukt
    0.30
     transcendence
    0.30
    POSITIVE LOGITS
     this
    0.38
     fhe
    0.36
     এই
    0.36
     This
    0.36
    This
    0.34
     the
    0.34
     cette
    0.34
     इस
    0.33
     този
    0.33
    この
    0.33
    Act Density 0.105%

    No Known Activations