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

    Neuronpedia

    INDEX
    Explanations

    Negative feelings/situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讀
    -0.08
     лаборатор
    -0.07
    lüğü
    -0.07
     conc
    -0.06
     fantast
    -0.06
    _gc
    -0.06
     *_
    -0.06
     çek
    -0.06
     �
    -0.06
    )!=
    -0.06
    POSITIVE LOGITS
     arbitr
    0.07
    ινη
    0.07
    mir
    0.06
    EdgeInsets
    0.06
    システム
    0.06
    github
    0.06
    _event
    0.06
    ивают
    0.06
    datum
    0.06
    ramework
    0.06
    Act Density 0.049%

    No Known Activations