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

    Neuronpedia

    INDEX
    Explanations

    State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bitur
    -0.66
     Houſe
    -0.65
     Efq
    -0.65
     Италијани
    -0.65
     onOptions
    -0.63
     myſelf
    -0.61
     Monfieur
    -0.60
     Diſ
    -0.59
    Salta
    -0.57
     ſche
    -0.57
    POSITIVE LOGITS
     الحره
    0.59
    الحياه
    0.57
    kuuta
    0.54
     <<<<<<<<<<<<<<
    0.54
    ign
    0.52
    EndInit
    0.50
    yadh
    0.49
    vants
    0.48
    converting
    0.48
     potong
    0.47
    Act Density 1.480%

    No Known Activations