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

    Neuronpedia

    INDEX
    Explanations

    seeking specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tc
    0.49
    xymatrix
    0.42
    AIRMAN
    0.39
     basilaires
    0.39
     букмекерлик
    0.39
    क्ष्य
    0.39
    ையில்
    0.38
     sólo
    0.38
    ţiile
    0.38
    తన
    0.38
    POSITIVE LOGITS
     their
    0.44
     Innov
    0.41
     leurs
    0.40
     их
    0.39
     Civic
    0.39
     नौकर
    0.39
     loro
    0.38
     leur
    0.38
     get
    0.38
     WE
    0.38
    Act Density 0.001%

    No Known Activations