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

    Neuronpedia

    INDEX
    Explanations

    programming code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     r
    0.55
     observers
    0.51
     data
    0.50
     Ic
    0.50
     Visualization
    0.49
     Observ
    0.49
    <blockquote>
    0.49
     observ
    0.47
     um
    0.47
    CoV
    0.47
    POSITIVE LOGITS
    ி
    0.62
    بیداری
    0.59
    льнай
    0.59
    woorden
    0.55
    તના
    0.53
    preferably
    0.53
    ․
    0.52
    ться
    0.52
    ằng
    0.51
    magic
    0.50
    Act Density 0.001%

    No Known Activations