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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fast
    -0.07
    amat
    -0.06
    };↵↵
    -0.06
    _EFFECT
    -0.06
    'It
    -0.06
     Sponge
    -0.06
    gate
    -0.06
     intention
    -0.06
     이야
    -0.06
    gif
    -0.06
    POSITIVE LOGITS
     самом
    0.07
     موسیقی
    0.07
     compareTo
    0.06
     Орг
    0.06
     enormously
    0.06
    	import
    0.06
     kind
    0.06
     KD
    0.06
     confident
    0.06
     weakest
    0.06
    Act Density 0.007%

    No Known Activations