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

    Neuronpedia

    INDEX
    Explanations

    rated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "But
    -0.08
    عار
    -0.07
     GCBO
    -0.07
    加工
    -0.06
    _groups
    -0.06
     nelze
    -0.06
    _cmds
    -0.06
    Buscar
    -0.06
     gearbox
    -0.06
    trasound
    -0.06
    POSITIVE LOGITS
     Afr
    0.08
     barrage
    0.07
     tariff
    0.07
     Camb
    0.06
     RATE
    0.06
    ations
    0.06
     Esc
    0.06
    357
    0.06
    cribe
    0.06
     rated
    0.06
    Act Density 0.004%

    No Known Activations