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

    Neuronpedia

    INDEX
    Explanations

    rinse after second

    np_acts-logits-general · gemini-2.5-flash-lite

    debugger, release, tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.57
    6
    0.54
    4
    0.50
    an
    0.49
    5
    0.48
    8
    0.47
     algebras
    0.46
    9
    0.46
    U
    0.45
    R
    0.43
    POSITIVE LOGITS
     agua
    0.52
     طبي
    0.48
     rápidamente
    0.47
     água
    0.47
     دي
    0.46
     começ
    0.44
    بي
    0.44
     很
    0.44
     bạn
    0.43
     它
    0.43
    Act Density 0.000%

    No Known Activations