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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knih
    -0.07
     Damian
    -0.07
    miner
    -0.06
    oste
    -0.06
    jab
    -0.06
    _mar
    -0.06
    uar
    -0.06
    ega
    -0.06
    .Feed
    -0.06
    _flux
    -0.06
    POSITIVE LOGITS
     LOGIN
    0.07
    (Sql
    0.07
    (`/
    0.07
    end
    0.07
    ulnerable
    0.07
     RFID
    0.06
    -selection
    0.06
    RID
    0.06
     jpeg
    0.06
     TB
    0.06
    Act Density 0.060%

    No Known Activations