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

    Neuronpedia

    INDEX
    Explanations

    Code and forum posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .events
    -0.08
    Probe
    -0.07
    🦀
    -0.07
    巴拉
    -0.07
     conjug
    -0.07
    uiltin
    -0.07
     практически
    -0.07
    癌症
    -0.07
     bounce
    -0.07
    (content
    -0.07
    POSITIVE LOGITS
    };
↵
    0.07
     commission
    0.07
    ]){
↵
    0.07
    >())
    0.07
     });
↵
    0.07
    )};↵
    0.07
    :eq
    0.06
    ととも
    0.06
    ">↵
    0.06
    ,");↵
    0.06
    Act Density 0.000%

    No Known Activations