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

    Neuronpedia

    INDEX
    Explanations

    it's raining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이는
    0.79
    Conversely
    0.77
     والتي
    0.77
    を用いた
    0.76
     شاهد
    0.76
    自身の
    0.75
     stvari
    0.75
     coloro
    0.73
     tycker
    0.73
    icularly
    0.73
    POSITIVE LOGITS
     supposed
    1.44
     gonna
    1.40
     been
    1.33
     raining
    1.32
     happening
    1.31
     going
    1.25
     snowing
    1.20
     hopeless
    1.12
     gotta
    1.08
     called
    1.06
    Act Density 0.329%

    No Known Activations