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

    Neuronpedia

    INDEX
    Explanations

    Scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Returned
    -0.07
    بان
    -0.07
     TRY
    -0.07
    θο
    -0.06
     Amsterdam
    -0.06
    spam
    -0.06
    _more
    -0.06
     indentation
    -0.06
     tm
    -0.06
     hasattr
    -0.06
    POSITIVE LOGITS
    ิเคราะห
    0.06
     Riot
    0.06
     Sec
    0.06
     Originally
    0.06
     stě
    0.06
     일반
    0.06
    0.06
                    
    0.06
     fifo
    0.06
    	description
    0.06
    Act Density 0.067%

    No Known Activations