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

    Neuronpedia

    INDEX
    Explanations

    instruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _effect
    -0.06
    แก
    -0.06
    ятно
    -0.06
    Meet
    -0.06
    'u
    -0.06
    .Tab
    -0.06
    esti
    -0.05
    Ul
    -0.05
     concede
    -0.05
     AccessToken
    -0.05
    POSITIVE LOGITS
     Electrical
    0.07
    анд
    0.07
     Placement
    0.07
    lor
    0.07
     bóng
    0.07
     VX
    0.06
     Behaviour
    0.06
     -=
    0.06
    _SCHEDULE
    0.06
     nord
    0.06
    Act Density 0.006%

    No Known Activations