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

    Neuronpedia

    INDEX
    Explanations

    horizontal line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -box
    -0.07
     Copper
    -0.07
     Sodium
    -0.07
     nail
    -0.07
     cooker
    -0.07
     causal
    -0.07
     Edison
    -0.06
     kim
    -0.06
    \f
    -0.06
     Uzbek
    -0.06
    POSITIVE LOGITS
    شت
    0.08
    ại
    0.07
    /animations
    0.07
    163
    0.07
    LOS
    0.07
    Mont
    0.07
     непосред
    0.07
                    
    0.07
    esimal
    0.07
    antd
    0.07
    Act Density 0.007%

    No Known Activations