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

    Neuronpedia

    INDEX
    Explanations

    Errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     країн
    -0.07
     });
↵
    -0.06
    楼
    -0.06
    morgan
    -0.06
     resta
    -0.06
     기자
    -0.06
    ')}>↵
    -0.06
    \Factory
    -0.06
     bakeka
    -0.06
     strncpy
    -0.06
    POSITIVE LOGITS
    Fresh
    0.07
     gaps
    0.07
     erase
    0.07
     cruel
    0.06
    (with
    0.06
    ίνει
    0.06
    generate
    0.06
     domain
    0.06
     lapse
    0.06
     covenant
    0.06
    Act Density 0.000%

    No Known Activations