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

    Neuronpedia

    INDEX
    Explanations

    strive for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     azione
    0.53
     Balliye
    0.51
    oine
    0.50
    seti
    0.50
     воздей
    0.49
     വ്യത്യ
    0.49
     искать
    0.49
    password
    0.49
     informe
    0.48
    ബർ
    0.48
    POSITIVE LOGITS
     pumpkin
    0.47
     pumpkins
    0.47
     jerky
    0.46
     galloping
    0.46
     pathway
    0.46
     lif
    0.45
     Pumpkin
    0.44
     measured
    0.43
     distracting
    0.42
     cun
    0.42
    Act Density 0.000%

    No Known Activations