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

    Neuronpedia

    INDEX
    Explanations

    currency amounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    자가
    -0.07
    PHONE
    -0.07
    _geo
    -0.07
     sewage
    -0.07
     astronomers
    -0.07
     scholarships
    -0.07
     washer
    -0.06
    EHICLE
    -0.06
    олож
    -0.06
    NECTION
    -0.06
    POSITIVE LOGITS
    young
    0.07
    -П
    0.07
    geb
    0.06
     oblig
    0.06
    筋
    0.06
    侍
    0.06
    <Account
    0.06
     coment
    0.06
    mie
    0.06
     numar
    0.06
    Act Density 0.035%

    No Known Activations