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

    Neuronpedia

    INDEX
    Explanations

    citation references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nsic
    -0.07
    免疫
    -0.07
     microbi
    -0.07
    防火
    -0.07
    盗窃
    -0.07
    婧
    -0.07
    装载
    -0.07
     Gall
    -0.07
    偿
    -0.07
    _SAMPL
    -0.06
    POSITIVE LOGITS
     праз
    0.08
    幢
    0.07
    ORK
    0.07
     adventurous
    0.07
     futuristic
    0.07
     оказыва
    0.07
     began
    0.07
     LENGTH
    0.07
     anticipated
    0.07
     WORK
    0.06
    Act Density 0.009%

    No Known Activations