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

    Neuronpedia

    INDEX
    Explanations

    pressure, refusal, control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")]
    0.39
    quad
    0.39
    angle
    0.38
     Review
    0.38
    十六
    0.36
     Exped
    0.36
    க்கப்பட்ட
    0.35
    的使用
    0.35
     AM
    0.35
     Minority
    0.35
    POSITIVE LOGITS
     bram
    0.48
    ராஜ
    0.45
    بي
    0.44
     chin
    0.44
     bedside
    0.44
     wildest
    0.44
    ется
    0.42
     breathes
    0.42
     गौर
    0.42
    ן
    0.42
    Act Density 0.000%

    No Known Activations