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

    Neuronpedia

    INDEX
    Explanations

    classification metrics and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    し
    0.41
    리아
    0.40
    레
    0.39
     kys
    0.38
    Week
    0.36
     че
    0.36
    keys
    0.35
    ÃO
    0.35
    Comput
    0.35
    há
    0.34
    POSITIVE LOGITS
    ammlung
    0.47
                                  
    0.44
    iftoire
    0.44
     Franck
    0.43
    🎑
    0.43
    ädt
    0.43
     Bluff
    0.41
     thirteenth
    0.40
                                   
    0.40
     dispoz
    0.40
    Act Density 0.007%

    No Known Activations