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

    Neuronpedia

    INDEX
    Explanations

    file(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thermometer
    0.45
     thermometers
    0.41
     conserva
    0.40
     игровой
    0.39
     gay
    0.39
     discretionary
    0.39
     data
    0.38
     arena
    0.37
    సు
    0.37
    ियाणा
    0.37
    POSITIVE LOGITS
    ål
    0.44
    ë
    0.40
     schönen
    0.39
    Mount
    0.39
    ïdes
    0.38
    ichert
    0.38
    健全
    0.38
     schöne
    0.38
    Having
    0.37
    ängen
    0.37
    Act Density 0.004%

    No Known Activations