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

    Neuronpedia

    INDEX
    Explanations

    Questions and conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EST
    -0.07
     disgusted
    -0.07
     עצמם
    -0.07
    迷惑
    -0.07
     newspapers
    -0.07
    🤐
    -0.06
    愧
    -0.06
    ￣
    -0.06
     מישהו
    -0.06
     płyt
    -0.06
    POSITIVE LOGITS
     belie
    0.08
    (Contact
    0.07
    (alpha
    0.07
     bypass
    0.07
     incontr
    0.07
    balance
    0.07
     Load
    0.07
    bundle
    0.07
    pixels
    0.07
     DON
    0.07
    Act Density 0.063%

    No Known Activations