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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PD
    -0.07
     DEA
    -0.07
     Numeric
    -0.07
    犯罪
    -0.07
     hormones
    -0.07
    ysics
    -0.07
    .ContextCompat
    -0.07
     सक
    -0.07
    zp
    -0.06
     artery
    -0.06
    POSITIVE LOGITS
     �
    0.07
     agreements
    0.06
    _outputs
    0.06
    äge
    0.06
     embodiments
    0.06
     Achie
    0.06
     brasile
    0.06
    finding
    0.05
     pry
    0.05
     Apart
    0.05
    Act Density 0.023%

    No Known Activations