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

    Neuronpedia

    INDEX
    Explanations

    hands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >>↵
    -0.06
     indie
    -0.06
    dater
    -0.06
    Telefone
    -0.06
    ]:↵
    -0.06
    ,:);↵
    -0.06
     tome
    -0.06
    ]:↵↵
    -0.06
    IENTATION
    -0.06
     haunting
    -0.06
    POSITIVE LOGITS
     implicit
    0.06
    afka
    0.06
    .One
    0.06
     عضو
    0.06
    .General
    0.06
     perg
    0.06
     Conditioning
    0.06
     attribution
    0.06
     Robotics
    0.06
    ्ड
    0.06
    Act Density 0.014%

    No Known Activations