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

    Neuronpedia

    INDEX
    Explanations

    linked list operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovania
    0.40
     नाउ
    0.40
    ően
    0.40
    ᅣ
    0.40
    лькі
    0.39
    postdata
    0.38
     herself
    0.38
    soaked
    0.38
    āk
    0.36
     EXEMPLARY
    0.36
    POSITIVE LOGITS
     jego
    0.50
     njegov
    0.43
    Bet
    0.42
     jeho
    0.42
    Aust
    0.41
     Jego
    0.41
     Alb
    0.41
    Valid
    0.40
    Alb
    0.40
     his
    0.39
    Act Density 0.007%

    No Known Activations