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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Specs
    -0.07
     만들어
    -0.07
    849
    -0.06
    yers
    -0.06
     исч
    -0.06
    .In
    -0.06
    ुलन
    -0.06
     соглас
    -0.06
     �
    -0.06
    -0.06
    POSITIVE LOGITS
    lycer
    0.06
     oppression
    0.06
    scient
    0.06
     bài
    0.06
     awarded
    0.06
    .Fatalf
    0.05
    _thread
    0.05
     Borough
    0.05
     happ
    0.05
    นา
    0.05
    Act Density 0.070%

    No Known Activations