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

    Neuronpedia

    INDEX
    Explanations

    caregiver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _issue
    -0.07
    :'#
    -0.07
     dra
    -0.07
    🔄
    -0.07
    %',
    -0.07
     feels
    -0.07
    全新的
    -0.07
    &t
    -0.07
    🦊
    -0.07
     Enlight
    -0.06
    POSITIVE LOGITS
    berger
    0.08
     Ger
    0.07
     Son
    0.07
    康
    0.07
    器
    0.07
     kommen
    0.07
    쨕
    0.07
    PH
    0.07
     çağrı
    0.07
     Parkinson
    0.07
    Act Density 0.003%

    No Known Activations