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

    Neuronpedia

    INDEX
    Explanations

    confirm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    untos
    -0.07
    Cad
    -0.07
     Vapor
    -0.07
     avoidance
    -0.07
    _three
    -0.06
    xml
    -0.06
    ющих
    -0.06
    _graphics
    -0.06
     Cad
    -0.06
    \Field
    -0.06
    POSITIVE LOGITS
    verified
    0.08
    ('')↵
    0.07
     confirmed
    0.06
     απο
    0.06
    '];↵↵
    0.06
    ันต
    0.06
     uy
    0.06
    악
    0.06
    ======↵
    0.06
    -many
    0.06
    Act Density 0.071%

    No Known Activations