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

    Neuronpedia

    INDEX
    Explanations

    code blocks and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diarrh
    0.40
    URNIZOR
    0.38
    <unused639>
    0.38
     vertebr
    0.38
     protéines
    0.37
    Mâc
    0.37
    STTS
    0.37
     prostat
    0.37
     vaisse
    0.36
    SERVICIO
    0.36
    POSITIVE LOGITS
    ↵
    0.62
            
    0.57
    //
    0.54
        
    0.53
    try
    0.51
    if
    0.51
               
    0.50
    """
    0.50
     {
    0.49
              
    0.47
    Act Density 0.375%

    No Known Activations