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

    Neuronpedia

    INDEX
    Explanations

    LOCATION

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?,?,?,?,
    -0.06
     trä
    -0.06
    .setLevel
    -0.06
     chỉ
    -0.06
     counterfeit
    -0.06
     komb
    -0.06
    styles
    -0.06
    Việc
    -0.06
    それは
    -0.06
     jeu
    -0.06
    POSITIVE LOGITS
     Limit
    0.08
    Constraints
    0.07
     Depression
    0.07
    appable
    0.07
     Conduct
    0.07
    lname
    0.06
     accidentally
    0.06
    utherford
    0.06
     Vital
    0.06
    -la
    0.06
    Act Density 0.103%

    No Known Activations