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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,↵
    -0.07
     eject
    -0.07
    _gamma
    -0.07
    E
    -0.06
    ्तन
    -0.06
     Refriger
    -0.06
    ]
    -0.06
    ",↵
    -0.06
     Sisters
    -0.06
    _gui
    -0.06
    POSITIVE LOGITS
     dysfunctional
    0.07
     боя
    0.07
     SEEK
    0.07
     rodz
    0.06
     يا
    0.06
    cycl
    0.06
    役
    0.06
     мест
    0.06
     nichž
    0.06
     смерти
    0.06
    Act Density 0.001%

    No Known Activations