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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ts
    -0.06
     guarding
    -0.06
     rainy
    -0.06
    itemId
    -0.06
     occupational
    -0.06
    ssel
    -0.06
    Appointment
    -0.06
     drilled
    -0.06
    opathy
    -0.06
     Wald
    -0.06
    POSITIVE LOGITS
     लगत
    0.07
    ]').
    0.07
    737
    0.07
    /j
    0.06
    озвращ
    0.06
     j
    0.06
    ��
    0.06
    _NOTICE
    0.06
    limitations
    0.06
    (&(
    0.06
    Act Density 0.005%

    No Known Activations