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

    Neuronpedia

    INDEX
    Explanations

    word pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🔰
    1.38
    😛
    1.37
    ❇
    1.37
     uranium
    1.35
     cleavage
    1.35
     beige
    1.31
     tomar
    1.30
    😧
    1.29
     cosmic
    1.29
     epistem
    1.29
    POSITIVE LOGITS
    Re
    1.93
    Un
    1.90
    Res
    1.84
    Real
    1.76
    Dest
    1.74
    Min
    1.74
    Not
    1.72
    Sub
    1.69
    End
    1.68
    Soft
    1.67
    Act Density 0.227%

    No Known Activations