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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     types
    -0.50
    '
    -0.49
    .
    -0.48
    mdi
    -0.48
    ■
    -0.47
    WriteLiteral
    -0.46
     readings
    -0.46
     statements
    -0.45
     comments
    -0.45
     limits
    -0.44
    POSITIVE LOGITS
     propOrder
    0.82
     '\\;'
    0.80
    MLLoader
    0.79
    ⓧ
    0.78
     صوتيه
    0.76
    ]";
    0.71
    fjspx
    0.68
    Chham
    0.68
    tvguidetime
    0.66
    IntoConstraints
    0.66
    Act Density 0.036%

    No Known Activations