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

    Neuronpedia

    INDEX
    Explanations

    face masks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calibrate
    0.50
     prescribe
    0.50
    perimeter
    0.50
    End
    0.50
     Microphone
    0.48
    Camera
    0.48
    Cliente
    0.48
     sequentially
    0.48
    ❿
    0.48
     thrilled
    0.47
    POSITIVE LOGITS
     நமது
    0.51
    𝙠
    0.51
    特集
    0.50
    ir
    0.50
     बढ़ने
    0.50
    ovaniyu
    0.50
    kke
    0.49
     empowering
    0.49
     స్ప
    0.49
     bolstering
    0.49
    Act Density 0.002%

    No Known Activations