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

    Neuronpedia

    INDEX
    Explanations

    Technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	username
    -0.07
    _reward
    -0.07
    .digest
    -0.06
    averse
    -0.06
    .Server
    -0.06
    ://${
    -0.06
    .end
    -0.06
    .(
    -0.06
    UserName
    -0.06
    .Total
    -0.06
    POSITIVE LOGITS
     GLUT
    0.07
     radically
    0.06
    ώσεις
    0.06
    _URI
    0.06
    틱
    0.06
     WOM
    0.06
     understood
    0.06
     可
    0.06
     उन
    0.06
    Typography
    0.06
    Act Density 0.588%

    No Known Activations