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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saites
    -0.79
     الحره
    -0.76
    AccessorTable
    -0.72
     feroit
    -0.70
    Personensuche
    -0.69
    VersionUID
    -0.69
     okuyayım
    -0.69
     Extragalactic
    -0.69
     nationaux
    -0.68
     juridiques
    -0.68
    POSITIVE LOGITS
    ed
    0.56
    imp
    0.46
    sten
    0.45
    imo
    0.43
    laba
    0.43
    im
    0.43
     discovery
    0.43
    ep
    0.43
    ims
    0.43
    脚注
    0.43
    Act Density 0.645%

    No Known Activations