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

    Neuronpedia

    INDEX
    Explanations

    You

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Projection
    -0.08
    引爆
    -0.07
     confidence
    -0.07
     smiles
    -0.07
    	password
    -0.07
     enhances
    -0.07
     prosper
    -0.07
    peed
    -0.07
     explodes
    -0.07
    	fd
    -0.07
    POSITIVE LOGITS
     nightlife
    0.07
    现实生活
    0.07
    .fast
    0.06
    doctrine
    0.06
    eeee
    0.06
     Practical
    0.06
    .Groups
    0.06
    也没
    0.06
     Idea
    0.06
    _CBC
    0.06
    Act Density 0.037%

    No Known Activations