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

    Neuronpedia

    INDEX
    Explanations

    similarity between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entrando
    0.41
     Brim
    0.39
    িপ
    0.37
     понрави
    0.37
    clave
    0.37
    нке
    0.36
    tren
    0.36
     taf
    0.36
     tren
    0.36
     ryt
    0.36
    POSITIVE LOGITS
     servings
    0.43
     REACTORS
    0.39
     रोमांटिक
    0.39
     zerstört
    0.38
     stacks
    0.38
     defList
    0.37
    opak
    0.37
    諌
    0.36
     romantic
    0.36
     completes
    0.36
    Act Density 0.000%

    No Known Activations