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

    Neuronpedia

    INDEX
    Explanations

    Trump, White House

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acceptance
    -0.06
    insky
    -0.06
     مرگ
    -0.06
     outros
    -0.06
     Snapdragon
    -0.06
    -suite
    -0.06
    爸
    -0.06
    enser
    -0.06
    Friends
    -0.06
    macı
    -0.06
    POSITIVE LOGITS
     يج
    0.07
     нал
    0.07
    %%*/
    0.07
    .Error
    0.07
    AA
    0.06
     smoking
    0.06
     ratt
    0.06
    ulled
    0.06
    .GetValue
    0.06
    getNode
    0.06
    Act Density 0.005%

    No Known Activations