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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    撮
    -0.07
    _DIAG
    -0.06
    pone
    -0.06
    illos
    -0.06
                     
    -0.06
    าอ
    -0.06
    went
    -0.06
    	J
    -0.05
    -0.05
    	Event
    -0.05
    POSITIVE LOGITS
     dny
    0.07
    _empty
    0.07
    GM
    0.06
     цієї
    0.06
    [:-
    0.06
     quickly
    0.06
     яв
    0.06
     dns
    0.06
    ennes
    0.06
     \$
    0.06
    Act Density 0.018%

    No Known Activations