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

    Neuronpedia

    INDEX
    Explanations

    ervation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gin
    -0.07
    PILE
    -0.07
     düzenli
    -0.07
     hoch
    -0.06
     mys
    -0.06
    しない
    -0.06
    .onView
    -0.06
    FUNCTION
    -0.06
    uegos
    -0.06
    cls
    -0.06
    POSITIVE LOGITS
     fucks
    0.07
     Christianity
    0.06
    он
    0.06
     同
    0.06
    regn
    0.06
    _AUT
    0.06
     towards
    0.06
     typings
    0.06
     intermittent
    0.06
    487
    0.06
    Act Density 0.040%

    No Known Activations