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

    Neuronpedia

    INDEX
    Explanations

    opportunity project experience activity country city

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udes
    -0.10
    :
    -0.09
    oin
    -0.09
     ::
    -0.09
    osit
    -0.09
     (!
    -0.08
     ok
    -0.08
    ï¼¹
    -0.08
     Bloody
    -0.08
     inst
    -0.08
    POSITIVE LOGITS
     indeed
    0.17
    inde
    0.12
    å°¤
    0.12
     especially
    0.10
    iel
    0.10
    especially
    0.10
     worth
    0.09
     Indeed
    0.09
    ziel
    0.09
    inx
    0.09
    Act Density 0.192%

    No Known Activations