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

    Neuronpedia

    INDEX
    Explanations

    rare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    潼
    -0.07
    blocks
    -0.07
     Posting
    -0.07
    招
    -0.07
    萌
    -0.07
    fill
    -0.06
    通风
    -0.06
    аци
    -0.06
    lead
    -0.06
    .mem
    -0.06
    POSITIVE LOGITS
    nięcie
    0.08
    PointerType
    0.07
     фор
    0.07
     runaway
    0.07
     napisał
    0.07
    笯
    0.07
     álbum
    0.07
     caregiver
    0.07
     jako
    0.07
     backup
    0.07
    Act Density 0.149%

    No Known Activations