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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     matrimon
    -0.07
    repo
    -0.07
    bersome
    -0.06
     téc
    -0.06
    ونت
    -0.06
    /card
    -0.06
    亞
    -0.06
     Variety
    -0.06
    “A
    -0.06
     오후
    -0.06
    POSITIVE LOGITS
    registration
    0.06
     btn
    0.06
     vows
    0.06
    usted
    0.06
     hes
    0.06
    ые
    0.06
     logged
    0.06
     Concern
    0.06
     CTL
    0.06
     gitti
    0.06
    Act Density 0.109%

    No Known Activations