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

    Neuronpedia

    INDEX
    Explanations

    floor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stdio
    -0.07
    费用
    -0.07
    ós
    -0.07
    cao
    -0.07
     Xm
    -0.07
     exemplo
    -0.07
    ">
↵
↵
    -0.07
     descricao
    -0.07
    -quality
    -0.07
    ✓
    -0.06
    POSITIVE LOGITS
     slightly
    0.07
    噩
    0.07
    -before
    0.07
     stehen
    0.07
     Beginner
    0.06
    руж
    0.06
    альн
    0.06
    0.06
    釜
    0.06
    _recipe
    0.06
    Act Density 0.005%

    No Known Activations