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

    Neuronpedia

    INDEX
    Explanations

    case numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bois
    -0.80
     arra
    -0.76
     Emmanuel
    -0.73
     پسر
    -0.72
    alloy
    -0.72
    greek
    -0.71
    Kingston
    -0.71
    TTE
    -0.71
     Kingston
    -0.70
    stephen
    -0.70
    POSITIVE LOGITS
     Toolbox
    0.66
    虏
    0.64
     bền
    0.64
     equilibria
    0.63
    తి
    0.63
    Hrsg
    0.63
    マシン
    0.63
    ioren
    0.61
     whereby
    0.60
    DoesNotExist
    0.60
    Act Density 0.065%

    No Known Activations