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

    Neuronpedia

    INDEX
    Explanations

    graphics and math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ּוֹ
    -1.03
    Londres
    -0.91
     вызывает
    -0.90
    atorul
    -0.88
     菇
    -0.88
     mosa
    -0.87
    Beschreibung
    -0.86
     dök
    -0.86
     garcía
    -0.85
     unsplash
    -0.85
    POSITIVE LOGITS
     logistic
    0.96
     Math
    0.92
     Jul
    0.91
    root
    0.91
    aaa
    0.91
    KeyPressed
    0.91
    *.
    0.90
     God
    0.89
    ɑ
    0.88
     geral
    0.88
    Act Density 0.017%

    No Known Activations