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

    Neuronpedia

    INDEX
    Explanations

    muscular

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amenti
    -0.07
     disappointing
    -0.06
    ，现在
    -0.06
     encompasses
    -0.06
    room
    -0.06
    лемент
    -0.06
    rant
    -0.06
    	intent
    -0.06
     replication
    -0.06
     其
    -0.06
    POSITIVE LOGITS
    (__
    0.08
     muscular
    0.07
    _nonce
    0.07
    运
    0.07
    <LM
    0.07
    Г
    0.06
    .AddScoped
    0.06
     multim
    0.06
     ống
    0.06
     ('\
    0.06
    Act Density 0.006%

    No Known Activations