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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    userid
    -0.07
    步
    -0.07
     fluffy
    -0.06
    SUCCESS
    -0.06
     Movie
    -0.06
    .pth
    -0.06
     Romanian
    -0.06
    Mo
    -0.06
    _unique
    -0.06
    ptic
    -0.06
    POSITIVE LOGITS
     deadline
    0.07
     outreach
    0.07
    [((
    0.07
    ाधन
    0.06
     verilm
    0.06
    /community
    0.06
    _armor
    0.06
    ∏
    0.06
    
    0.06
     bize
    0.06
    Act Density 0.012%

    No Known Activations