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

    Neuronpedia

    INDEX
    Explanations

    git branch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1002>
    0.75
     george
    0.70
    <unused667>
    0.66
     surging
    0.65
     сучас
    0.64
    京
    0.64
     adentro
    0.64
    George
    0.64
    loaders
    0.63
    Checkbox
    0.62
    POSITIVE LOGITS
    卟
    0.71
    ifikation
    0.71
     arrived
    0.70
    曷
    0.69
     stayed
    0.69
    柟
    0.69
     posed
    0.68
    ysh
    0.67
    itute
    0.67
    tegr
    0.66
    Act Density 0.001%

    No Known Activations