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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.11
     /
    0.95
     x
    0.89
     {
    0.83
     [
    0.82
     rocks
    0.80
     i
    0.80
     true
    0.80
     `
    0.80
     *
    0.79
    POSITIVE LOGITS
        
    1.51
    Since
    1.50
    We
    1.49
    ----------------
    1.46
    Financial
    1.42
            
    1.40
    Un
    1.39
    This
    1.39
    The
    1.37
          
    1.36
    Act Density 0.465%

    No Known Activations