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

    Neuronpedia

    INDEX
    Explanations

    company descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crooked
    0.37
     hallucinations
    0.36
     thawing
    0.35
     aches
    0.35
     sluggish
    0.34
     cataracts
    0.33
     distorted
    0.33
     tears
    0.33
     surroundings
    0.32
     flashbacks
    0.32
    POSITIVE LOGITS
     Corporation
    0.47
    公司
    0.41
     specializes
    0.40
    成立于
    0.40
     corporation
    0.39
    公司的
    0.39
     நிறுவனம்
    0.39
     empresa
    0.39
     CORPORATION
    0.38
     Ltd
    0.38
    Act Density 0.033%

    No Known Activations