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

    Neuronpedia

    INDEX
    Explanations

    [citation needed]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    plist
    0.38
    plemente
    0.38
    ovine
    0.37
    atuak
    0.37
     opted
    0.37
     championship
    0.36
    erm
    0.35
    ður
    0.34
    herst
    0.34
    antown
    0.34
    POSITIVE LOGITS
    citation
    0.57
     verify
    0.54
     citation
    0.54
    Verify
    0.54
     verificare
    0.53
     citations
    0.52
     needing
    0.51
     verification
    0.50
    Verification
    0.50
     Verify
    0.49
    Act Density 0.001%

    No Known Activations