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

    Neuronpedia

    INDEX
    Explanations

    national

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UserScript
    -0.92
    IntoConstraints
    -0.87
     محفوظة
    -0.82
    findpost
    -0.81
    tvguidetime
    -0.81
    GIH
    -0.77
    曖昧さ回避
    -0.75
    
    -0.75
    хьтан
    -0.75
     téléphonique
    -0.74
    POSITIVE LOGITS
    ↵↵
    0.54
    ↵
    0.48
    ..
    0.45
    <eos>
    0.44
    ...
    0.42
    ↵↵↵
    0.40
     em
    0.38
    ),
    0.38
    );
    0.37
     {});
    0.36
    Act Density 0.006%

    No Known Activations