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

    Neuronpedia

    INDEX
    Explanations

    grammatically correct sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Se
    -0.08
    せ
    -0.08
     Se
    -0.07
     Cultural
    -0.07
     derby
    -0.07
    717
    -0.07
     reported
    -0.07
     Верхов
    -0.07
    �
    -0.06
     ser
    -0.06
    POSITIVE LOGITS
    اكن
    0.07
    Destructor
    0.06
    -dismiss
    0.06
    (OP
    0.06
    名無しさん
    0.06
     downside
    0.06
    .Comp
    0.06
     ภ
    0.06
    .desktop
    0.06
     několik
    0.06
    Act Density 0.072%

    No Known Activations