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

    Neuronpedia

    INDEX
    Explanations

    verified expert opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    飘
    0.41
    रावट
    0.41
    便利な
    0.38
     honorary
    0.38
    冲突
    0.38
     उपयोगी
    0.38
     kuhusu
    0.38
    Useful
    0.37
    穸
    0.37
     raging
    0.37
    POSITIVE LOGITS
     verified
    0.63
     Verification
    0.54
    verified
    0.54
     verification
    0.53
     verifies
    0.52
    Verified
    0.52
     curated
    0.49
     Verified
    0.48
     Opinions
    0.46
    Verification
    0.44
    Act Density 0.000%

    No Known Activations