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

    Neuronpedia

    INDEX
    Explanations

    obtained

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _UNUSED
    -0.07
    Dependency
    -0.07
     خواب
    -0.07
     annoyance
    -0.06
     dere
    -0.06
    uy�
    -0.06
     Audit
    -0.06
    ChangeEvent
    -0.06
     Clint
    -0.06
    621
    -0.06
    POSITIVE LOGITS
    -n
    0.06
     itibar
    0.06
     Barrel
    0.06
    deş
    0.06
    _cp
    0.06
    .proj
    0.06
     прием
    0.06
    梯
    0.06
    明白
    0.06
     ألمان
    0.06
    Act Density 0.049%

    No Known Activations