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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    airie
    -0.07
     repeal
    -0.06
    AAC
    -0.06
    npc
    -0.06
     осуществ
    -0.06
    "After
    -0.06
    esity
    -0.06
    alli
    -0.06
    ＿＿
    -0.06
    ysters
    -0.06
    POSITIVE LOGITS
     Hide
    0.08
     ese
    0.07
     Hedge
    0.07
     Revised
    0.06
    (B
    0.06
    leading
    0.06
    jun
    0.06
    Unified
    0.06
     decrypted
    0.06
     multiple
    0.06
    Act Density 0.009%

    No Known Activations