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

    Neuronpedia

    INDEX
    Explanations

    limitation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .metamodel
    -0.06
    	Context
    -0.06
    \Factory
    -0.06
    _copy
    -0.06
     Télé
    -0.06
     type
    -0.06
     sqr
    -0.06
    	timeout
    -0.06
    noise
    -0.06
     analog
    -0.06
    POSITIVE LOGITS
     přih
    0.07
    ίκη
    0.07
    acker
    0.07
    ака
    0.07
     kterých
    0.07
    ایت
    0.06
     Tweet
    0.06
    codile
    0.06
     actress
    0.06
    τέρα
    0.06
    Act Density 0.007%

    No Known Activations