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

    Neuronpedia

    INDEX
    Explanations

    guid: XXXXXXXX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ី
    -0.72
    จำ
    -0.68
     Sammy
    -0.68
     neutrality
    -0.67
     kutumia
    -0.67
    華
    -0.66
    Terra
    -0.65
    WHITE
    -0.65
    âteau
    -0.65
    اني
    -0.65
    POSITIVE LOGITS
    倶
    0.77
     SYNC
    0.71
    Ck
    0.71
     PRIVACY
    0.70
     responses
    0.68
    pleft
    0.66
     Globals
    0.66
     Crea
    0.66
    Lamp
    0.65
    dox
    0.64
    Act Density 0.046%

    No Known Activations