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

    Neuronpedia

    INDEX
    Explanations

    mathematical/scientific proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vari
    -0.09
    \Command
    -0.07
     vari
    -0.07
     pleg
    -0.07
    مله
    -0.07
    .prototype
    -0.07
     기타
    -0.07
     cayó
    -0.07
     Vari
    -0.07
     sueños
    -0.07
    POSITIVE LOGITS
    今回は
    0.08
     aangezien
    0.08
    	debug
    0.08
    quer
    0.08
    rtl
    0.08
     hotspot
    0.08
    ekin
    0.08
    _<
    0.08
     hotspots
    0.08
    	handler
    0.07
    Act Density 0.000%

    No Known Activations