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

    Neuronpedia

    INDEX
    Explanations

    multilingual diverse words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.55
     meltdown
    0.44
    Vs
    0.43
     bailout
    0.43
     lobby
    0.42
     fund
    0.42
     bell
    0.41
     system
    0.41
    天才
    0.41
     fleet
    0.41
    POSITIVE LOGITS
    மக்கள்
    0.53
     Bhagava
    0.52
    विक
    0.51
    cheek
    0.50
     күзгү
    0.50
     autant
    0.49
    一张
    0.49
     miteinander
    0.49
     Pache
    0.49
    இர
    0.48
    Act Density 0.000%

    No Known Activations