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

    Neuronpedia

    INDEX
    Explanations

    Album

    np_max-act · gemini-2.0-flash

    This neuron activates on the document’s “Album” mentions—i.e. the label or heading that marks an album title or album‐related metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    reach
    -0.07
    nature
    -0.07
    ştır
    -0.07
    INUX
    -0.07
     DESIGN
    -0.07
     Wire
    -0.07
     Woodward
    -0.07
     Tort
    -0.07
    Repair
    -0.07
     Kiss
    -0.07
    POSITIVE LOGITS
    album
    0.10
     album
    0.08
     albums
    0.08
    .album
    0.07
    블
    0.07
     Album
    0.07
    Album
    0.07
    albums
    0.06
     alıyor
    0.06
    uel
    0.06
    Act Density 0.008%

    No Known Activations