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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Helpful
    0.44
     edited
    0.44
    Editing
    0.43
     Playing
    0.42
     altered
    0.41
     ойнойт
    0.40
     altercation
    0.40
    Modified
    0.39
    edited
    0.39
    Playing
    0.38
    POSITIVE LOGITS
     build
    1.00
    建立
    0.92
    build
    0.89
    Build
    0.84
     cultivate
    0.84
     establish
    0.83
     develop
    0.82
     foster
    0.82
     Build
    0.81
     membangun
    0.81
    Act Density 0.296%

    No Known Activations