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

    Neuronpedia

    INDEX
    Explanations

    testing and code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बीत
    0.45
    ֮
    0.44
    㫧
    0.43
     Deposits
    0.43
     absorbance
    0.42
     waveforms
    0.42
     distress
    0.40
    ri
    0.40
     businesses
    0.40
    媇
    0.39
    POSITIVE LOGITS
    EL
    0.49
    INSON
    0.43
    quinazolin
    0.42
     Guinea
    0.41
    懸
    0.40
    手指
    0.40
     jako
    0.40
    াদশ
    0.40
     vede
    0.39
     Bourgoin
    0.39
    Act Density 0.002%

    No Known Activations