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

    Neuronpedia

    INDEX
    Explanations

    refusal of harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    藓
    0.67
    efois
    0.66
    ashire
    0.66
    ꯕ
    0.66
    plicial
    0.62
    ibalsan
    0.61
    foils
    0.61
    نمية
    0.60
    ariski
    0.60
    seid
    0.60
    POSITIVE LOGITS
     true
    0.79
     beautiful
    0.73
     this
    0.72
     what
    0.72
    ↵
    0.71
    0.69
     picture
    0.68
      
    0.66
    /
    0.65
     everyday
    0.61
    Act Density 0.048%

    No Known Activations