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

    Neuronpedia

    INDEX
    Explanations

    likeness or feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anses
    0.29
    被称为
    0.26
     Starting
    0.26
     ইহাদের
    0.25
     consideramos
    0.25
     Featuring
    0.25
    featuring
    0.24
     Effective
    0.24
    ीय
    0.24
     Regarding
    0.24
    POSITIVE LOGITS
     like
    0.71
     seperti
    0.50
     như
    0.48
    Like
    0.47
     مثل
    0.46
    像是
    0.46
     जैसे
    0.43
    like
    0.42
     comme
    0.42
     como
    0.42
    Act Density 0.102%

    No Known Activations