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

    Neuronpedia

    INDEX
    Explanations

    responding to user input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rest
    -0.07
     nitrogen
    -0.07
     Vol
    -0.07
     compan
    -0.07
     restore
    -0.07
     conjunto
    -0.07
     Proto
    -0.07
     Firefox
    -0.07
     subsidiary
    -0.07
    为主
    -0.07
    POSITIVE LOGITS
    🥋
    0.08
    쯕
    0.07
    刑侦
    0.07
    ей
    0.07
     LOVE
    0.07
     componentDid
    0.07
    ⤵
    0.07
    כך
    0.07
    言い
    0.07
    ☧
    0.06
    Act Density 0.116%

    No Known Activations