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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uka
    -0.06
    体
    -0.06
     subsection
    -0.06
    н
    -0.06
    turn
    -0.06
    Hack
    -0.06
     worms
    -0.06
     exemption
    -0.06
     competit
    -0.06
    section
    -0.06
    POSITIVE LOGITS
     заболеваний
    0.08
    newValue
    0.07
    ΙΑΚ
    0.07
    SFML
    0.06
    steder
    0.06
    orage
    0.06
    _BLOCKS
    0.06
     imperialism
    0.06
    вих
    0.06
    uvian
    0.06
    Act Density 0.092%

    No Known Activations