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

    Neuronpedia

    INDEX
    Explanations

    News and Articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odynamic
    -0.08
     대
    -0.08
     dermat
    -0.07
     stringWithFormat
    -0.07
     Secretary
    -0.07
     Modification
    -0.07
     chancellor
    -0.07
    物理
    -0.07
     Darwin
    -0.07
    dorf
    -0.06
    POSITIVE LOGITS
    .MEDIA
    0.08
    	ResultSet
    0.07
    Began
    0.07
    akan
    0.06
    Connections
    0.06
    imestep
    0.06
     insult
    0.06
     cam
    0.06
    **
↵
    0.06
    sk
    0.06
    Act Density 0.041%

    No Known Activations