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

    Neuronpedia

    INDEX
    Explanations

    Survey

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Behavior
    0.65
    icultural
    0.58
    avement
    0.57
     lọc
    0.57
    routine
    0.56
    covering
    0.56
    行為
    0.55
     Asphalt
    0.55
    ietic
    0.55
    otherapeutic
    0.55
    POSITIVE LOGITS
     palk
    0.59
    Env
    0.58
     able
    0.56
     Sachsen
    0.56
     sdk
    0.55
    下了
    0.55
     env
    0.54
     SDK
    0.54
    нець
    0.54
    fk
    0.54
    Act Density 0.001%

    No Known Activations