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

    Neuronpedia

    INDEX
    Explanations

    conceptual learning templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     svim
    0.40
    ొప్పి
    0.40
     intervalles
    0.39
     pasan
    0.39
     achats
    0.38
    rishna
    0.38
     mengisi
    0.38
     godinu
    0.38
     sees
    0.38
    рованным
    0.38
    POSITIVE LOGITS
    Learning
    0.59
     Learning
    0.59
     template
    0.53
    Template
    0.51
     Template
    0.50
    Group
    0.47
    Templates
    0.47
     Templates
    0.46
    Query
    0.45
    template
    0.45
    Act Density 0.001%

    No Known Activations