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

    Neuronpedia

    INDEX
    Explanations

    i followed by message, in, can, am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    are
    0.88
    d
    0.70
    网上
    0.67
    ართ
    0.65
     arthrop
    0.65
     Lux
    0.64
    সভ
    0.64
     propi
    0.63
    tions
    0.63
     aran
    0.63
    POSITIVE LOGITS
     am
    1.32
    roquois
    1.22
     think
    1.11
    ota
    1.04
    çin
    1.04
    ridium
    1.04
    verm
    1.02
    RELAND
    0.99
    amb
    0.93
     guess
    0.92
    Act Density 0.349%

    No Known Activations