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

    Neuronpedia

    INDEX
    Explanations

    code structure context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sim
    0.38
    ri
    0.37
    தே
    0.37
    mc
    0.36
     Sim
    0.36
     alcohol
    0.36
     toys
    0.35
     aquarium
    0.35
    tay
    0.35
     alternatives
    0.35
    POSITIVE LOGITS
    HashCode
    0.32
    南海
    0.32
    Countryside
    0.32
     चंद्रशेखर
    0.32
    Divide
    0.31
     قریب
    0.31
    쳤
    0.31
    了出来
    0.31
    ⑨
    0.30
    zeption
    0.30
    Act Density 0.039%

    No Known Activations