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

    Neuronpedia

    INDEX
    Explanations

    say *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     graduate
    -0.07
    ío
    -0.07
    _than
    -0.06
     roses
    -0.06
     מישה
    -0.06
     Wonder
    -0.06
    edicine
    -0.06
     나는
    -0.06
    开辟
    -0.06
     mal
    -0.06
    POSITIVE LOGITS
    桶
    0.07
    库
    0.07
    companies
    0.07
    不间
    0.07
    =&
    0.07
    ｾ
    0.06
    莶
    0.06
     miệ
    0.06
    ByteArray
    0.06
    됬
    0.06
    Act Density 0.000%

    No Known Activations