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

    Neuronpedia

    INDEX
    Explanations

    new york place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    leman
    0.44
    枴
    0.40
    ┳
    0.40
     chrom
    0.40
    richtungen
    0.39
     परिवर्तन
    0.37
     ใคร
    0.37
    ObjectURL
    0.37
    ellik
    0.36
     Solving
    0.36
    POSITIVE LOGITS
     Troy
    0.61
     Colon
    0.57
     Mechanic
    0.57
     Latham
    0.55
     Hoos
    0.54
     Rens
    0.54
    Troy
    0.54
     colon
    0.53
     Lansing
    0.51
     Nis
    0.50
    Act Density 0.002%

    No Known Activations