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

    Neuronpedia

    INDEX
    Explanations

    mathematics and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    还
    -0.07
     Chap
    -0.07
    Win
    -0.07
     Rot
    -0.07
    .mid
    -0.07
    administr
    -0.07
    (Me
    -0.06
     ecx
    -0.06
    _Man
    -0.06
     MPU
    -0.06
    POSITIVE LOGITS
    电话
    0.07
    添加剂
    0.07
    indsight
    0.07
    -driven
    0.07
    space
    0.07
    andum
    0.07
     detergent
    0.06
     Source
    0.06
    下称
    0.06
    (phone
    0.06
    Act Density 0.020%

    No Known Activations