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

    Neuronpedia

    INDEX
    Explanations

    conclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burb
    -0.07
    Often
    -0.07
     deutschland
    -0.06
    HEET
    -0.06
    itempty
    -0.06
     Violet
    -0.06
     Jed
    -0.06
     Spokane
    -0.06
     outbound
    -0.06
    createQuery
    -0.06
    POSITIVE LOGITS
    quez
    0.07
    さ
    0.07
    _ALWAYS
    0.07
     vines
    0.06
    _di
    0.06
     instantiated
    0.06
    _SU
    0.06
    slick
    0.06
     ASM
    0.06
     insights
    0.06
    Act Density 0.001%

    No Known Activations