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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besoin
    -0.07
    containers
    -0.06
     ngồi
    -0.06
     спеці
    -0.06
    ้าว
    -0.06
     outr
    -0.06
    .Pointer
    -0.06
    .Driver
    -0.06
     后
    -0.06
    젠
    -0.06
    POSITIVE LOGITS
    Amt
    0.07
    ...]
    0.06
     professor
    0.06
    Collections
    0.06
    �认
    0.06
    SENS
    0.06
    _PUSH
    0.06
     Lifestyle
    0.06
    �
    0.06
    _TRNS
    0.06
    Act Density 0.032%

    No Known Activations