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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Painlev
    0.43
     singularities
    0.43
     apostila
    0.43
     vacuoles
    0.42
     sapon
    0.41
     själ
    0.41
     logarith
    0.40
     thisobject
    0.40
     carbonates
    0.40
     그리고
    0.40
    POSITIVE LOGITS
            
    0.52
    lin
    0.48
    clear
    0.47
    ↵
    0.46
    K
    0.45
                                   
    0.44
        
    0.44
     Clear
    0.43
     Felt
    0.41
    ry
    0.41
    Act Density 0.007%

    No Known Activations