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

    Neuronpedia

    INDEX
    Explanations

    stricter CSP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    you
    0.49
    mor
    0.48
    kah
    0.47
    fork
    0.47
    socket
    0.47
    aca
    0.46
     a
    0.46
    esto
    0.45
    0
    0.45
     you
    0.44
    POSITIVE LOGITS
     Manufact
    0.55
    ،
    0.53
     Aless
    0.52
     Sincerely
    0.51
     Wissenschaft
    0.50
    новним
    0.50
     Konstant
    0.48
     Automobiles
    0.48
     Elke
    0.48
     Engen
    0.48
    Act Density 0.000%

    No Known Activations