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

    Neuronpedia

    INDEX
    Explanations

    names and associated surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Deze
    0.26
    輋
    0.25
    웡
    0.24
    Für
    0.24
     Flücht
    0.24
    Penumpang
    0.23
    Capabilities
    0.23
    მწიფ
    0.22
    Lä
    0.22
    Đối
    0.22
    POSITIVE LOGITS
     was
    0.23
     member
    0.22
    amino
    0.21
     som
    0.21
    and
    0.21
     is
    0.21
     curator
    0.21
     were
    0.21
     provider
    0.21
    in
    0.20
    Act Density 0.000%

    No Known Activations