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

    Neuronpedia

    INDEX
    Explanations

    understanding queries or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nett
    0.49
    netz
    0.48
     ਆਪਣ
    0.46
    ennzeichnet
    0.45
    lovepoetry
    0.45
    conoc
    0.45
     ServicePolicy
    0.44
     ఆరోగ్య
    0.44
    rond
    0.44
    נ
    0.44
    POSITIVE LOGITS
     conspired
    0.51
     money
    0.50
     plucked
    0.49
     clerk
    0.47
     clas
    0.46
     civil
    0.46
     extracts
    0.44
     conjunction
    0.44
     excerpts
    0.43
     sculptures
    0.43
    Act Density 0.004%

    No Known Activations