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

    Neuronpedia

    INDEX
    Explanations

    purpose and usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Θε
    0.40
     Conch
    0.39
     còn
    0.39
     echoing
    0.39
    薢
    0.38
     Ignore
    0.38
     กิน
    0.38
     आंसर
    0.38
     let
    0.37
    然后
    0.37
    POSITIVE LOGITS
     upotre
    0.49
     примене
    0.47
     situations
    0.46
     seasons
    0.46
    idados
    0.44
     შემთხვევ
    0.44
     použit
    0.44
     commercial
    0.43
     industries
    0.43
    használ
    0.43
    Act Density 0.004%

    No Known Activations