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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amina
    -0.07
     Wick
    -0.06
     gifted
    -0.06
    .padding
    -0.06
     athlete
    -0.06
     Santana
    -0.06
    ічних
    -0.06
     р
    -0.06
    ‌ش
    -0.06
     tung
    -0.06
    POSITIVE LOGITS
    _VC
    0.07
    SSF
    0.07
     mềm
    0.06
    섭
    0.06
     ceasefire
    0.06
    [Unit
    0.06
    _NPC
    0.06
     renk
    0.06
    _highlight
    0.06
    DeviceInfo
    0.06
    Act Density 0.019%

    No Known Activations