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

    Neuronpedia

    INDEX
    Explanations

    will remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gifter
    0.29
     twinning
    0.28
     annuities
    0.28
     annuity
    0.27
    ĐT
    0.27
    JSPA
    0.27
    ્ટ
    0.27
    ائب
    0.26
    agge
    0.26
    tede
    0.26
    POSITIVE LOGITS
     bleiben
    0.24
     .
    0.24
     quedaron
    0.24
     Tan
    0.23
     parecen
    0.23
     Ng
    0.22
    vor
    0.22
    Ob
    0.22
     H
    0.22
     Y
    0.22
    Act Density 0.000%

    No Known Activations