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

    Neuronpedia

    INDEX
    Explanations

    formal greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ânea
    0.98
    écies
    0.89
    ichlor
    0.84
    ossos
    0.84
     partes
    0.84
    osaurs
    0.84
     parti
    0.83
    BAD
    0.83
     unten
    0.82
     vuoi
    0.82
    POSITIVE LOGITS
     dear
    1.42
     sir
    1.37
     Dear
    1.21
    Dear
    1.18
     Sir
    1.13
    Sir
    1.10
     dearest
    1.07
     Mr
    1.06
     darling
    1.05
     Madam
    1.00
    Act Density 0.084%

    No Known Activations