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

    Neuronpedia

    INDEX
    Explanations

    sports players' names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ngh
    0.51
     Gemeinde
    0.50
     kommen
    0.49
     meu
    0.48
    istische
    0.47
    錤
    0.47
     mein
    0.47
     Clemente
    0.47
    నా
    0.46
     Gettys
    0.46
    POSITIVE LOGITS
    Coverage
    0.48
     velocities
    0.47
    fastq
    0.46
    hydes
    0.43
    Exceptions
    0.43
    Forest
    0.42
    ोज
    0.42
    防火
    0.41
    balances
    0.41
    kis
    0.41
    Act Density 0.001%

    No Known Activations