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

    Neuronpedia

    INDEX
    Explanations

    fr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *)((
    -0.07
    ила
    -0.07
    _controls
    -0.07
    .executor
    -0.06
     tall
    -0.06
    (password
    -0.06
     christmas
    -0.06
     landed
    -0.06
    итет
    -0.06
    StatusCode
    -0.06
    POSITIVE LOGITS
    FR
    0.07
     FR
    0.07
     olay
    0.07
     fif
    0.07
    _SR
    0.07
     Challenger
    0.07
     fringe
    0.07
     frei
    0.06
     arising
    0.06
     поля
    0.06
    Act Density 0.022%

    No Known Activations