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

    Neuronpedia

    INDEX
    Explanations

    Anecdotes and personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odian
    -0.07
    _loading
    -0.06
     cmdline
    -0.06
    новид
    -0.06
    Nil
    -0.06
    но
    -0.06
    vana
    -0.06
    uish
    -0.06
    iteli
    -0.06
    amaged
    -0.06
    POSITIVE LOGITS
     الشركة
    0.07
     legitimately
    0.07
    /.
    0.07
    		
↵
↵
    0.07
    640
    0.06
    �
    0.06
     disqualified
    0.06
               
↵
    0.06
     @"";↵
    0.06
    997
    0.06
    Act Density 0.003%

    No Known Activations