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

    Neuronpedia

    INDEX
    Explanations

    listing or enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೇವ
    0.49
    oluminescence
    0.48
    ра
    0.45
    Cread
    0.43
    ဝ်
    0.43
     zerstört
    0.43
     congratulate
    0.42
    ចប់
    0.42
    vergne
    0.42
     dönt
    0.41
    POSITIVE LOGITS
    에
    0.55
     briefs
    0.51
    वाहक
    0.49
    issimus
    0.48
     bunches
    0.48
     경로
    0.47
     Realms
    0.47
     areas
    0.46
     electrop
    0.46
    メリ
    0.46
    Act Density 0.000%

    No Known Activations