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

    Neuronpedia

    INDEX
    Explanations

    build, deploy, and install commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vicepresidente
    0.69
     vacancy
    0.68
    вающих
    0.65
     absc
    0.64
    ABS
    0.63
     allegiance
    0.63
     papp
    0.63
     absorbent
    0.63
     consciousness
    0.62
    mother
    0.62
    POSITIVE LOGITS
     deploy
    1.28
     build
    1.25
     Build
    1.20
    build
    1.20
    Build
    1.19
    编译
    1.11
    deploy
    1.11
     构建
    1.10
    Deploy
    1.10
     builds
    1.08
    Act Density 0.129%

    No Known Activations