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

    Neuronpedia

    INDEX
    Explanations

    trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     environments
    -0.08
     Ich
    -0.08
    加快推进
    -0.07
    .is
    -0.07
     assurance
    -0.07
    โปร
    -0.07
    �
    -0.07
    令
    -0.07
    𝐼
    -0.07
     implementing
    -0.07
    POSITIVE LOGITS
    ơ
    0.07
     Hick
    0.07
     pn
    0.07
     Chapel
    0.07
     viene
    0.07
    /************************
    0.07
     Border
    0.06
    خير
    0.06
    air
    0.06
    uckle
    0.06
    Act Density 0.010%

    No Known Activations