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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Integrity
    -0.07
     Battle
    -0.06
     put
    -0.06
     gastr
    -0.06
     Dry
    -0.06
     colore
    -0.06
     Tools
    -0.06
    (inter
    -0.06
     seem
    -0.06
    Keys
    -0.06
    POSITIVE LOGITS
    ]|[
    0.07
    ick
    0.07
    .githubusercontent
    0.07
     История
    0.06
    ImageUrl
    0.06
    ційного
    0.06
     Lemma
    0.06
    оличество
    0.06
    aged
    0.06
     ас
    0.06
    Act Density 0.054%

    No Known Activations