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

    Neuronpedia

    INDEX
    Explanations

    phrases like "related to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ricult
    0.47
     pager
    0.46
     feminine
    0.45
    ぜひ
    0.44
     masculine
    0.43
     専用
    0.43
     multimedia
    0.42
     biasanya
    0.42
     generalmente
    0.41
     heterocyclic
    0.41
    POSITIVE LOGITS
    Returning
    0.50
    Kle
    0.47
    Change
    0.44
    재
    0.43
    oll
    0.42
    处罚
    0.42
    CODE
    0.42
    prett
    0.41
    getName
    0.41
    ef
    0.41
    Act Density 0.004%

    No Known Activations