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

    Neuronpedia

    INDEX
    Explanations

    orthorhombic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lek
    -0.07
     analyzing
    -0.07
    טלוויזיה
    -0.07
    vak
    -0.06
     assaulting
    -0.06
    -
    -0.06
     Nguy
    -0.06
     Notice
    -0.06
     DAY
    -0.06
    ())
↵
    -0.06
    POSITIVE LOGITS
    .strategy
    0.06
    >Returns
    0.06
     Spiritual
    0.06
     يقوم
    0.06
     crc
    0.06
    横向
    0.06
    إمكانية
    0.06
     DECL
    0.06
    ғ
    0.06
     sứ
    0.06
    Act Density 0.001%

    No Known Activations