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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strategic
    -0.07
    ,map
    -0.07
     Indonesian
    -0.07
     Barney
    -0.07
    ="<
    -0.06
    enor
    -0.06
    מיטב
    -0.06
    ỏ
    -0.06
    =username
    -0.06
    ests
    -0.06
    POSITIVE LOGITS
    株洲
    0.07
    昆仑
    0.07
    市级
    0.07
     nâng
    0.07
    AccessException
    0.07
    行业的
    0.06
    悬挂
    0.06
    EntityManager
    0.06
     subway
    0.06
    нятие
    0.06
    Act Density 0.003%

    No Known Activations