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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     externi
    -0.67
    WebVitals
    -0.65
    <bos>
    -0.64
     north
    -0.64
    SourceChecksum
    -0.63
    nodoc
    -0.62
    stdc
    -0.59
     northwest
    -0.59
    UnusedPrivate
    -0.58
     StatelessWidget
    -0.57
    POSITIVE LOGITS
    wards
    0.67
    ability
    0.58
     America
    0.55
    PhysRev
    0.54
    sal
    0.49
    ACHUSET
    0.49
    andte
    0.49
    oneofs
    0.48
    glDelete
    0.48
    hoppers
    0.48
    Act Density 0.021%

    No Known Activations