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

    Neuronpedia

    INDEX
    Explanations

    define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    define
    -0.94
     CURIAM
    -0.81
    tagHelperRunner
    -0.79
    #+#
    -0.69
    :+:
    -0.64
     hObject
    -0.63
    sticks
    -0.62
    XmlAccessType
    -0.60
     الحره
    -0.59
     externi
    -0.59
    POSITIVE LOGITS
     gear
    0.52
    åk
    0.52
     للمعارف
    0.51
    ive
    0.49
    et
    0.47
    المكان
    0.47
    fromnode
    0.47
     Bal
    0.45
    Bal
    0.44
    acc
    0.43
    Act Density 0.330%

    No Known Activations