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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debout
    -0.71
     avoient
    -0.61
     aveug
    -0.60
     boire
    -0.60
     giustizia
    -0.60
     quitté
    -0.60
     ainfi
    -0.59
     noires
    -0.57
     retenir
    -0.57
    ẠI
    -0.57
    POSITIVE LOGITS
     Infórmanos
    0.66
    /**
    0.56
    ValueStyle
    0.56
    서
    0.50
    DatabaseError
    0.48
    ttino
    0.46
    ⮕
    0.45
    вен
    0.44
     CreateTagHelper
    0.44
    conductors
    0.44
    Act Density 0.062%

    No Known Activations