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

    Neuronpedia

    INDEX
    Explanations

    conditions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فهم
    0.47
    Ს
    0.47
    🦗
    0.46
     kesin
    0.46
    เติม
    0.45
     Humanos
    0.44
     அறிந்து
    0.44
    睇
    0.44
     Recognizing
    0.44
    そも
    0.43
    POSITIVE LOGITS
     *
    0.47
    ,
    0.47
     spotlights
    0.46
    -
    0.45
     milder
    0.45
     stations
    0.40
    aser
    0.40
     computer
    0.40
     sparking
    0.40
     computers
    0.39
    Act Density 0.002%

    No Known Activations