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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rhs
    -0.07
    opcion
    -0.06
    ្�
    -0.06
    .dirty
    -0.06
     brawl
    -0.06
    N
    -0.06
    兵
    -0.06
    ],"
    -0.06
    peat
    -0.06
     pH
    -0.06
    POSITIVE LOGITS
     somewhere
    0.07
     вам
    0.07
     recomend
    0.07
     teach
    0.07
    ([(
    0.06
     feasible
    0.06
    phthalm
    0.06
     Distribution
    0.06
     stockholm
    0.06
    hopefully
    0.06
    Act Density 0.003%

    No Known Activations