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

    Neuronpedia

    INDEX
    Explanations

    TypeScript 'any' type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     находится
    0.41
    ACI
    0.39
     distinguishes
    0.39
    Media
    0.37
     изуча
    0.36
    ANDS
    0.36
    Associ
    0.36
    IGI
    0.35
    Ghosts
    0.35
    Rig
    0.35
    POSITIVE LOGITS
     debilit
    0.48
    ellations
    0.40
    瞞
    0.40
    urados
    0.38
    禁用
    0.37
    Disable
    0.37
     alert
    0.36
    രെ
    0.36
     Disable
    0.36
    بان
    0.36
    Act Density 0.001%

    No Known Activations