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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     save
    -0.07
    /colors
    -0.07
     vest
    -0.06
    	ms
    -0.06
    Tester
    -0.06
     vig
    -0.06
    #↵
    -0.06
    .Setter
    -0.06
     expelled
    -0.06
    .Play
    -0.06
    POSITIVE LOGITS
    (*)(
    0.07
     mình
    0.06
    =''):↵
    0.06
     Reached
    0.06
     Ankara
    0.06
    ỗng
    0.06
    fall
    0.06
    onomic
    0.06
     UIStoryboard
    0.06
    clarations
    0.06
    Act Density 0.222%

    No Known Activations