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

    Neuronpedia

    INDEX
    Explanations

    intelligent design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Solo
    -0.08
     polož
    -0.08
     charbon
    -0.08
    solo
    -0.07
     어느
    -0.07
    ütter
    -0.07
    ılması
    -0.07
     pamph
    -0.07
    Solo
    -0.07
     disgrace
    -0.07
    POSITIVE LOGITS
     deus
    0.10
    .creator
    0.10
     beings
    0.09
     governing
    0.09
     Modimo
    0.09
     overseeing
    0.09
     सत्ता
    0.09
     Bondye
    0.09
     Deus
    0.09
     Tuhan
    0.09
    Act Density 0.017%

    No Known Activations