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

    Neuronpedia

    INDEX
    Explanations

    Tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aks
    -0.07
    _fee
    -0.06
     emploi
    -0.06
    pciones
    -0.06
     coats
    -0.06
     ورد
    -0.06
     multitude
    -0.06
     Curtis
    -0.05
    ()},↵
    -0.05
    _sound
    -0.05
    POSITIVE LOGITS
    寶
    0.07
    Looper
    0.07
     bueno
    0.07
    -fl
    0.07
    ButtonClick
    0.06
    егод
    0.06
     прох
    0.06
    brief
    0.06
     deser
    0.06
    IU
    0.06
    Act Density 0.050%

    No Known Activations