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

    Neuronpedia

    INDEX
    Explanations

    legal/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hern
    -0.07
    actic
    -0.07
    Weight
    -0.07
    -ro
    -0.07
     Đo
    -0.07
    -states
    -0.07
    jed
    -0.07
    άντα
    -0.07
    -question
    -0.06
    licable
    -0.06
    POSITIVE LOGITS
    Usu
    0.06
     semen
    0.06
    %)↵
    0.06
    �
    0.06
     swallow
    0.06
    (section
    0.06
    到底
    0.06
    ."+
    0.06
    %i
    0.06
     очевид
    0.05
    Act Density 0.000%

    No Known Activations