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

    Neuronpedia

    INDEX
    Explanations

    marriages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MODEL
    -0.06
     congressman
    -0.06
    	out
    -0.06
    median
    -0.06
     arrogance
    -0.06
     ADDRESS
    -0.06
     Nina
    -0.06
     Constructor
    -0.06
     CONTRACT
    -0.06
     Royal
    -0.05
    POSITIVE LOGITS
     گردد
    0.07
    력
    0.07
    اسیون
    0.07
    диви
    0.06
    genden
    0.06
    uy�
    0.06
     процессе
    0.06
     پاورپوینت
    0.06
    cordova
    0.06
    áln
    0.06
    Act Density 0.009%

    No Known Activations