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

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marcus
    -0.06
    ]).
    -0.06
    ()).
    -0.06
     laut
    -0.06
    umably
    -0.06
     Roch
    -0.06
     cach
    -0.06
    achusetts
    -0.06
    liers
    -0.05
     neutrality
    -0.05
    POSITIVE LOGITS
     Own
    0.07
     own
    0.07
    (sent
    0.07
    )))));
↵
    0.07
    -sign
    0.06
     owning
    0.06
    执
    0.06
     vlastní
    0.06
    频
    0.06
    ------↵↵
    0.06
    Act Density 0.004%

    No Known Activations