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
    oeff
    -0.07
    ож
    -0.06
    �
    -0.06
     cont
    -0.06
     dictionaries
    -0.06
     Portal
    -0.06
     其
    -0.06
     spontaneously
    -0.06
     cry
    -0.06
    	work
    -0.06
    POSITIVE LOGITS
    Knowledge
    0.07
    质
    0.06
    ARIANT
    0.06
    _vue
    0.06
    #End
    0.06
    plural
    0.06
    �
    0.06
     ACTIVE
    0.06
     -:-
    0.06
    _strings
    0.06
    Act Density 0.008%

    No Known Activations