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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash

    situations or clauses where expectations or conditions are being set or explained.

    oai_token-act-pair · gpt-4oTriggered by @tcai
    New Auto-Interp
    Negative Logits
    opard
    -0.07
     quicker
    -0.07
     înt
    -0.06
     unwitting
    -0.06
    <<<<
    -0.06
    itu
    -0.06
    orian
    -0.06
     undercut
    -0.06
    contrast
    -0.06
     finding
    -0.06
    POSITIVE LOGITS
     electoral
    0.07
     JAVA
    0.07
    기준
    0.07
     functionalities
    0.07
     Europe
    0.06
     standart
    0.06
     starts
    0.06
     minus
    0.06
     consumes
    0.06
     Financing
    0.06
    Act Density 6.431%

    No Known Activations