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

    Neuronpedia

    INDEX
    Explanations

    thrust, trust, think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     отказыва
    0.47
     Pressed
    0.46
    л
    0.46
    d
    0.44
     Mounted
    0.44
     Lorsqu
    0.43
     Razor
    0.43
    $.
    0.42
    ரும்
    0.42
     Whenever
    0.41
    POSITIVE LOGITS
     paciente
    0.48
    ಿಸಲ
    0.46
    enschutz
    0.44
     அலுவலக
    0.43
    ət
    0.43
    mostly
    0.42
     pemerintah
    0.42
    mainframe
    0.42
     showering
    0.42
     segu
    0.42
    Act Density 0.006%

    No Known Activations