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

    Neuronpedia

    INDEX
    Explanations

    beginning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ldap
    -0.07
    良
    -0.06
    碰
    -0.06
     Newtonsoft
    -0.06
    ToolStripMenuItem
    -0.06
    strcpy
    -0.06
    觉
    -0.06
    =mysqli
    -0.06
     UIB
    -0.06
    =read
    -0.06
    POSITIVE LOGITS
    nEnter
    0.07
    ��
    0.06
    _IB
    0.06
    AZ
    0.06
     века
    0.06
     Ç
    0.06
    خط
    0.06
    "On
    0.06
     remain
    0.06
     Edison
    0.06
    Act Density 0.017%

    No Known Activations