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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ep
    -0.07
    am
    -0.07
    x
    -0.07
     sod
    -0.06
    ปฏ
    -0.06
     bm
    -0.06
    ====
    -0.06
    쳄
    -0.06
    噫
    -0.06
    yn
    -0.06
    POSITIVE LOGITS
    contacts
    0.08
     affidavit
    0.07
    _abort
    0.07
    并向
    0.07
     Assurance
    0.07
    ília
    0.07
     ingress
    0.07
    _MAIL
    0.07
    صغر
    0.07
     motorcycle
    0.07
    Act Density 0.021%

    No Known Activations