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

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ((-
    -0.07
     rnd
    -0.07
    /--
    -0.06
    (),'
    -0.06
    ]=-
    -0.06
     "','
    -0.06
     Signup
    -0.06
    uft
    -0.06
    ΟΝ
    -0.06
    418
    -0.06
    POSITIVE LOGITS
     caramel
    0.07
    _est
    0.07
     trab
    0.07
            
↵        
↵
    0.07
    切
    0.07
    .getCell
    0.07
    trfs
    0.07
     emotional
    0.07
     evidently
    0.07
    سه
    0.06
    Act Density 0.015%

    No Known Activations