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

    Neuronpedia

    INDEX
    Explanations

    дан

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uc
    -0.06
    敌
    -0.06
     lai
    -0.06
     inse
    -0.06
    703
    -0.06
    exclusive
    -0.05
     Пів
    -0.05
     пят
    -0.05
    _projection
    -0.05
    ATFORM
    -0.05
    POSITIVE LOGITS
    _rd
    0.07
    dag
    0.07
    archives
    0.07
    .min
    0.07
     letter
    0.06
    modelName
    0.06
    .@
    0.06
     khoản
    0.06
    .archive
    0.06
    massage
    0.06
    Act Density 0.009%

    No Known Activations