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

    Neuronpedia

    INDEX
    Explanations

    early history and initial stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    狠狠
    0.50
    text
    0.49
    ama
    0.47
    ant
    0.47
    ieno
    0.46
    oter
    0.45
     также
    0.45
     also
    0.45
    ím
    0.44
    also
    0.44
    POSITIVE LOGITS
     pembuatan
    0.45
    ിലേക്ക്
    0.44
     CTRL
    0.44
    黍
    0.43
     Якщо
    0.42
     acontece
    0.41
     menjawab
    0.40
     Wanneer
    0.40
     dxf
    0.40
     vaš
    0.40
    Act Density 0.001%

    No Known Activations