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

    Neuronpedia

    INDEX
    Explanations

    ink

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eld
    -0.07
     german
    -0.07
    ген
    -0.07
    leigh
    -0.07
     BTN
    -0.07
     legs
    -0.06
    ари
    -0.06
    oles
    -0.06
    рел
    -0.06
     ushort
    -0.06
    POSITIVE LOGITS
    Ohio
    0.06
     PrintWriter
    0.06
    -res
    0.06
    kke
    0.06
     delve
    0.06
    ._
    0.06
     emphasis
    0.06
    Arizona
    0.06
    위원회
    0.06
    _instance
    0.06
    Act Density 0.004%

    No Known Activations