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

    Neuronpedia

    INDEX
    Explanations

    the first capital biggest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lä
    0.39
    v
    0.38
    på
    0.38
     fournis
    0.38
    این
    0.36
    hoz
    0.36
    Hej
    0.36
    ng
    0.36
     Są
    0.35
    که
    0.35
    POSITIVE LOGITS
     opposed
    0.44
    पति
    0.43
    ymmet
    0.42
     MLC
    0.42
     solcher
    0.41
     importantly
    0.40
     ответственность
    0.39
     przyczyn
    0.38
     stara
    0.38
     टी
    0.38
    Act Density 0.337%

    No Known Activations