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

    Neuronpedia

    INDEX
    Explanations

    historic and analog related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hobby
    0.38
    racting
    0.37
    𝐘
    0.36
    rek
    0.36
    械
    0.36
     Νο
    0.36
    an
    0.35
     hobby
    0.35
     newsletter
    0.34
     SOA
    0.34
    POSITIVE LOGITS
    穹
    0.40
     زائد
    0.36
     historischen
    0.36
    Cur
    0.35
     palaces
    0.35
    સ્પ
    0.35
     Genomic
    0.35
     reservoirs
    0.35
     focuss
    0.35
     responseObject
    0.35
    Act Density 0.003%

    No Known Activations