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

    Neuronpedia

    INDEX
    Explanations

    dictionary specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     KYC
    0.54
     AEW
    0.52
     MNIST
    0.51
     Seiko
    0.50
    墀
    0.50
     Diện
    0.50
     IntelliJ
    0.49
    Resizable
    0.48
     Ελλάδα
    0.48
    intellij
    0.47
    POSITIVE LOGITS
    pletely
    0.55
    ții
    0.55
    razioni
    0.53
    untos
    0.52
    uras
    0.51
    ixa
    0.51
    ouring
    0.51
    usuarios
    0.50
    itar
    0.50
    apat
    0.49
    Act Density 0.000%

    No Known Activations