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

    Neuronpedia

    INDEX
    Explanations

    dance with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conseguir
    0.86
    ะไร
    0.86
     regras
    0.85
     slashing
    0.82
    砝
    0.81
    সম্পাদকীয়
    0.80
    eras
    0.80
     securing
    0.79
     theseKeys
    0.78
     passt
    0.78
    POSITIVE LOGITS
    Along
    0.80
    U
    0.68
    S
    0.67
     Along
    0.67
    along
    0.65
    बता
    0.65
    <0xE2>
    0.64
    Urban
    0.64
     জানা
    0.62
    Em
    0.62
    Act Density 0.001%

    No Known Activations