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

    Neuronpedia

    INDEX
    Explanations

    software assembly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    危險
    -0.07
    "And
    -0.07
     prey
    -0.06
    slide
    -0.06
    _prom
    -0.06
    保驾护航
    -0.06
     rc
    -0.06
     edge
    -0.06
    𝅎
    -0.06
    /V
    -0.06
    POSITIVE LOGITS
     Após
    0.08
     bedeut
    0.07
    /Documents
    0.07
    熬夜
    0.07
    ModelAttribute
    0.07
    success
    0.07
    crap
    0.07
     staat
    0.07
    שול
    0.07
    ൽ
    0.07
    Act Density 0.000%

    No Known Activations